how to state a thesis in a research paper

Reference management. Clean and simple.

How to write a thesis statement + examples

What is a thesis statement?

Is a thesis statement a question, how do you write a good thesis statement, how do i know if my thesis statement is good, examples of thesis statements, helpful resources on how to write a thesis statement, frequently asked questions about writing a thesis statement, related articles.

A thesis statement is the main argument of your paper or thesis.

The thesis statement is one of the most important elements of any piece of academic writing . It is a brief statement of your paper’s main argument. Essentially, you are stating what you will be writing about.

You can see your thesis statement as an answer to a question. While it also contains the question, it should really give an answer to the question with new information and not just restate or reiterate it.

Your thesis statement is part of your introduction. Learn more about how to write a good thesis introduction in our introduction guide .

A thesis statement is not a question. A statement must be arguable and provable through evidence and analysis. While your thesis might stem from a research question, it should be in the form of a statement.

Tip: A thesis statement is typically 1-2 sentences. For a longer project like a thesis, the statement may be several sentences or a paragraph.

A good thesis statement needs to do the following:

• Condense the main idea of your thesis into one or two sentences.
• Answer your project’s main research question.
• Clearly state your position in relation to the topic .
• Make an argument that requires support or evidence.

Once you have written down a thesis statement, check if it fulfills the following criteria:

• Your statement needs to be provable by evidence. As an argument, a thesis statement needs to be debatable.
• Your statement needs to be precise. Do not give away too much information in the thesis statement and do not load it with unnecessary information.
• Your statement cannot say that one solution is simply right or simply wrong as a matter of fact. You should draw upon verified facts to persuade the reader of your solution, but you cannot just declare something as right or wrong.

As previously mentioned, your thesis statement should answer a question.

If the question is:

What do you think the City of New York should do to reduce traffic congestion?

A good thesis statement restates the question and answers it:

In this paper, I will argue that the City of New York should focus on providing exclusive lanes for public transport and adaptive traffic signals to reduce traffic congestion by the year 2035.

Here is another example. If the question is:

How can we end poverty?

A good thesis statement should give more than one solution to the problem in question:

In this paper, I will argue that introducing universal basic income can help reduce poverty and positively impact the way we work.

• The Writing Center of the University of North Carolina has a list of questions to ask to see if your thesis is strong .

A thesis statement is part of the introduction of your paper. It is usually found in the first or second paragraph to let the reader know your research purpose from the beginning.

In general, a thesis statement should have one or two sentences. But the length really depends on the overall length of your project. Take a look at our guide about the length of thesis statements for more insight on this topic.

Here is a list of Thesis Statement Examples that will help you understand better how to write them.

Every good essay should include a thesis statement as part of its introduction, no matter the academic level. Of course, if you are a high school student you are not expected to have the same type of thesis as a PhD student.

Here is a great YouTube tutorial showing How To Write An Essay: Thesis Statements .

Research Paper: A step-by-step guide: 3. Thesis Statement & Outline

• 1. Getting Started
• 2. Topic Ideas
• 3. Thesis Statement & Outline
• 4. Appropriate Sources
• 5. Search Techniques
• 6. Taking Notes & Documenting Sources
• 7. Evaluating Sources
• 8. Citations & Plagiarism
• 9. Writing Your Research Paper

About Thesis Statements

Qualities of a thesis statement.

Thesis statements:

• state the subject matter and main ideas of a paper.
• appear in the first paragraph and announces what you will discuss in your paper.
• define the scope and focus of your essay, and tells your reader what to expect.  
• are not a simple factual statement.  It is an assertion that states your claims and that you can prove with evidence.
• should be the product of research and your own critical thinking.
• can be very helpful in constructing an outline for your essay; for each point you make, ask yourself whether it is relevant to the thesis.

Steps you can use to create a thesis statement

1. Start out with the main topic and focus of your essay.

youth gangs + prevention and intervention programs

2. Make a claim or argument in one sentence.  It can be helpful to start with a question which you then turn into an argument

Can prevention and intervention programs stop youth gang activities?  How?  ►►►  "Prevention and intervention programs can stop youth gang activities by giving teens something else to do."

3. Revise the sentence by using specific terms.

"Early prevention programs in schools are the most effective way to prevent youth gang involvement by giving teens good activities that offer a path to success."

4. Further revise the sentence to cover the scope of your essay and make a strong statement.

"Among various prevention and intervention efforts that have been made to deal with the rapid growth of youth gangs, early school-based prevention programs are the most effective way to prevent youth gang involvement, which they do by giving teens meaningful activities that offer pathways to achievement and success."

5. Keep your thesis statement flexible and revise it as needed. In the process of researching and writing, you may find new information or refine your understanding of the topic.

You can view this short video for more tips on how to write a clear thesis statement.

An outline is the skeleton of your essay, in which you list the arguments and subtopics in a logical order. A good outline is an important element in writing a good paper. An outline helps to target your research areas, keep you within the scope without going off-track, and it can also help to keep your argument in good order when writing the essay.  Once your outline is in good shape, it is much easier to write your paper; you've already done most of the thinking, so you just need to fill in the outline with a paragraph for each point.

To write an outline: The most common way to write an outline is the list format.  List all the major topics and subtopics with the key points that support them. Put similar topics and points together and arrange them in a logical order.    Include an introduction, a body, and a conclusion. 

A list outline should arrange the main points or arguments in a hierarchical structure indicated by Roman numerals for main ideas (I, II, III...), capital letters for subtopics (A, B, C...), Arabic numerals for details (1,2,3...), and lower-case letters for fine details if needed (a,b,c...). This helps keep things organized.  

Here is a shortened example of an outline:

Introduction: background and thesis statement

I. First topic

1. Supporting evidence 2. Supporting evidence

II. Second Topic

III. Third Topic

I. Summarize the main points of your paper II. Restate your thesis in different words III. Make a strong final statement

You can see examples of a few different kinds of outlines and get more help at the Purdue OWL .

• << Previous: 2. Topic Ideas
• Next: 4. Appropriate Sources >>
• Last Updated: Apr 18, 2023 12:12 PM
• URL: https://butte.libguides.com/ResearchPaper

Purdue Online Writing Lab Purdue OWL® College of Liberal Arts

Tips and Examples for Writing Thesis Statements

Welcome to the Purdue OWL

This page is brought to you by the OWL at Purdue University. When printing this page, you must include the entire legal notice.

Copyright ©1995-2018 by The Writing Lab & The OWL at Purdue and Purdue University. All rights reserved. This material may not be published, reproduced, broadcast, rewritten, or redistributed without permission. Use of this site constitutes acceptance of our terms and conditions of fair use.

Tips for Writing Your Thesis Statement

1. Determine what kind of paper you are writing:

• An analytical paper breaks down an issue or an idea into its component parts, evaluates the issue or idea, and presents this breakdown and evaluation to the audience.
• An expository (explanatory) paper explains something to the audience.
• An argumentative paper makes a claim about a topic and justifies this claim with specific evidence. The claim could be an opinion, a policy proposal, an evaluation, a cause-and-effect statement, or an interpretation. The goal of the argumentative paper is to convince the audience that the claim is true based on the evidence provided.

If you are writing a text that does not fall under these three categories (e.g., a narrative), a thesis statement somewhere in the first paragraph could still be helpful to your reader.

2. Your thesis statement should be specific—it should cover only what you will discuss in your paper and should be supported with specific evidence.

3. The thesis statement usually appears at the end of the first paragraph of a paper.

4. Your topic may change as you write, so you may need to revise your thesis statement to reflect exactly what you have discussed in the paper.

Thesis Statement Examples

Example of an analytical thesis statement:

The paper that follows should:

• Explain the analysis of the college admission process
• Explain the challenge facing admissions counselors

Example of an expository (explanatory) thesis statement:

• Explain how students spend their time studying, attending class, and socializing with peers

Example of an argumentative thesis statement:

• Present an argument and give evidence to support the claim that students should pursue community projects before entering college

While Sandel argues that pursuing perfection through genetic engineering would decrease our sense of humility, he claims that the sense of solidarity we would lose is also important.

This thesis summarizes several points in Sandel’s argument, but it does not make a claim about how we should understand his argument. A reader who read Sandel’s argument would not also need to read an essay based on this descriptive thesis.  

Broad thesis (arguable, but difficult to support with evidence) 

Michael Sandel’s arguments about genetic engineering do not take into consideration all the relevant issues.

This is an arguable claim because it would be possible to argue against it by saying that Michael Sandel’s arguments do take all of the relevant issues into consideration. But the claim is too broad. Because the thesis does not specify which “issues” it is focused on—or why it matters if they are considered—readers won’t know what the rest of the essay will argue, and the writer won’t know what to focus on. If there is a particular issue that Sandel does not address, then a more specific version of the thesis would include that issue—hand an explanation of why it is important.  

Arguable thesis with analytical claim 

While Sandel argues persuasively that our instinct to “remake” (54) ourselves into something ever more perfect is a problem, his belief that we can always draw a line between what is medically necessary and what makes us simply “better than well” (51) is less convincing.

This is an arguable analytical claim. To argue for this claim, the essay writer will need to show how evidence from the article itself points to this interpretation. It’s also a reasonable scope for a thesis because it can be supported with evidence available in the text and is neither too broad nor too narrow.  

Arguable thesis with normative claim 

Given Sandel’s argument against genetic enhancement, we should not allow parents to decide on using Human Growth Hormone for their children.

This thesis tells us what we should do about a particular issue discussed in Sandel’s article, but it does not tell us how we should understand Sandel’s argument.  

Questions to ask about your thesis 

• Is the thesis truly arguable? Does it speak to a genuine dilemma in the source, or would most readers automatically agree with it?  
• Is the thesis too obvious? Again, would most or all readers agree with it without needing to see your argument?  
• Is the thesis complex enough to require a whole essay's worth of argument?  
• Is the thesis supportable with evidence from the text rather than with generalizations or outside research?  
• Would anyone want to read a paper in which this thesis was developed? That is, can you explain what this paper is adding to our understanding of a problem, question, or topic?
• picture_as_pdf Thesis

• Link to facebook
• Link to linkedin
• Link to twitter
• Link to youtube
• Writing Tips

How to Write a Thesis Statement for a Research Paper

4-minute read

• 26th July 2023

A strong thesis statement is the foundation of a successful research paper . The thesis gives focus to your ideas, engages readers, and sets the tone for the rest of the paper. You’ve spent substantial time and effort to craft a well-written and effective study , so you want your thesis statement to accurately reflect the impact of your work.

However, writing a thesis is often easier said than done. So if you’ve already got the arguments, the data, and the conclusions, keep scrolling for our straightforward guide on how to write a thesis statement for a research paper.

What Is a Thesis Statement?

A thesis statement is a clear and succinct assertion that presents the main argument or central idea of a research paper or other academic work. You usually find the thesis, which serves as a road map for the entire piece of writing, at the end of the introductory paragraph. The thesis also highlights the importance and relevance of the research topic , explaining why it’s worth studying and what impact it may have.

A good thesis statement also invites critical discussion and debate. Although your statement should provide a compelling argument , it should also inspire readers to engage with your ideas and potentially challenge or explore alternative viewpoints.

How to Write a Thesis Statement

Your thesis statement should outline the scope and boundaries of the paper and indicate what aspects of the topic you’ll cover. But now that you know what a good thesis statement entails, where should you start? Check out our series of steps below for help on writing an impactful thesis statement that accurately summarizes your research and arguments.

Understand the Purpose of Your Research

Before you can write a thesis statement, you need to understand the purpose and scope of your research. Pinpoint the specific topic or issue you’ll be exploring and the main objective of your paper. You should also familiarize yourself with the existing literature and research related to your topic because these will help you refine your focus and identify gaps in the existing knowledge that your research can address.

Consider the Impact of Your Research

Your thesis statement should answer the question, What is the relevance? – meaning it should tell the reader what the practical implications of your research are, why the research is significant, and what it adds to the broader academic landscape.

Find this useful?

Subscribe to our newsletter and get writing tips from our editors straight to your inbox.

Make a Concise Claim or Argument

Your statement should be clear, specific, and concise, conveying the main point of your research in one or two sentences. It should present a claim or argument that you’ll go on to support and defend in your paper, so avoid purely factual or self-evident statements. Be precise in your wording and tailor your thesis statement to the scope of your research – don’t introduce a new or unrelated topic that you don’t expressly address in your paper. The thesis statement is meant to indicate what the reader can expect to find in your paper, and you must support the thesis with evidence throughout.

Revise and Refine the Statement

Crafting a strong thesis statement may require multiple attempts, so take the time to revise and edit it until you’re satisfied that it meets your requirements.

Example Thesis Statement

Below is an example of a strong thesis statement that clearly emphasizes the main points of a research topic:

In this example, the thesis statement clearly identifies the main topic (technology’s impact on education) and presents a strong argument about technology’s positive effects. The thesis conveys the essential message of the research concisely in one sentence, leaving no doubt about the position of the author and what they’ll address in the paper.

Expert Editing Services

Ensure your research paper makes an impact by having our expert editors proofread it professionally. Our team has experience proofreading a variety of academic work, from research papers to dissertations to journal articles. Get started today by submitting your free sample of 500 words or less.

Share this article:

Post A New Comment

Got content that needs a quick turnaround? Let us polish your work. Explore our editorial business services.

2-minute read

How to Cite the CDC in APA

If you’re writing about health issues, you might need to reference the Centers for Disease...

5-minute read

Six Product Description Generator Tools for Your Product Copy

Introduction If you’re involved with ecommerce, you’re likely familiar with the often painstaking process of...

3-minute read

What Is a Content Editor?

Are you interested in learning more about the role of a content editor and the...

The Benefits of Using an Online Proofreading Service

Proofreading is important to ensure your writing is clear and concise for your readers. Whether...

6 Online AI Presentation Maker Tools

Creating presentations can be time-consuming and frustrating. Trying to construct a visually appealing and informative...

What Is Market Research?

No matter your industry, conducting market research helps you keep up to date with shifting...

Make sure your writing is the best it can be with our expert English proofreading and editing.

How to Write a Research Paper: Thesis Statement

• Anatomy of a Research Paper
• Developing a Research Focus
• Background Research Tips
• Searching Tips
• Scholarly Journals vs. Popular Journals
• Thesis Statement
• Annotated Bibliography
• Citing Sources
• Evaluating Sources
• Literature Review
• Academic Integrity
• Scholarship as Conversation
• Understanding Fake News
• Data, Information, Knowledge

What is a Thesis Statement?

What is a Thesis Statement?  

A thesis statement is a concise statement of an academic work's main point. The thesis statement should identify both what the paper is about (the topic) and what you are saying about it. Your thesis statement should be as specific as possible. For a short essay, the length of your thesis statement should be one or two sentences. If you are writing a dissertation or book, your thesis statement should be about a paragraph in length. A thesis should avoid saying "This paper is about..." Your thesis statement should be as specific as possible. 

A basic pattern to follow is "An analysis of (insert topic here) will show that (point one), (point two), and (point three)." Keep in mind this is only an example, there is no one-size-fits-all formula. 

Who Needs a Thesis Statement?

All academic writing, from a short essay to a dissertation or a monograph, should have an identifiable thesis statement somewhere in it. The longer or more complicated an academic work is, the easier is becomes to get bogged down in details and lose sight of the overall argument, and the more important it is to clearly state the central point. 

Where Should I Put My Thesis Statement? 

Thesis statements are most commonly located near the beginning of the academic work, usually towards the end of the introduction. This strategic placement allows the reader to quickly understand specifically what the essay is about and be able to follow the arguments as they are presented. 

Tips for Writing Your Thesis Statement

Tips and Examples for Writing Thesis Statements: Purdue Owl 

This resource from Purdue University's Online Writing Lab (OWL) provides tips for creating a thesis statement and examples of different types of thesis statements. 

• << Previous: Scholarly Journals vs. Popular Journals
• Next: Annotated Bibliography >>
• Last Updated: Apr 4, 2024 5:51 PM
• URL: https://libguide.umary.edu/researchpaper

• Walden University
• Faculty Portal

Writing a Paper: Thesis Statements

Basics of thesis statements.

The thesis statement is the brief articulation of your paper's central argument and purpose. You might hear it referred to as simply a "thesis." Every scholarly paper should have a thesis statement, and strong thesis statements are concise, specific, and arguable. Concise means the thesis is short: perhaps one or two sentences for a shorter paper. Specific means the thesis deals with a narrow and focused topic, appropriate to the paper's length. Arguable means that a scholar in your field could disagree (or perhaps already has!).

Strong thesis statements address specific intellectual questions, have clear positions, and use a structure that reflects the overall structure of the paper. Read on to learn more about constructing a strong thesis statement.

Being Specific

This thesis statement has no specific argument:

Needs Improvement: In this essay, I will examine two scholarly articles to find similarities and differences.

This statement is concise, but it is neither specific nor arguable—a reader might wonder, "Which scholarly articles? What is the topic of this paper? What field is the author writing in?" Additionally, the purpose of the paper—to "examine…to find similarities and differences" is not of a scholarly level. Identifying similarities and differences is a good first step, but strong academic argument goes further, analyzing what those similarities and differences might mean or imply.

Better: In this essay, I will argue that Bowler's (2003) autocratic management style, when coupled with Smith's (2007) theory of social cognition, can reduce the expenses associated with employee turnover.

The new revision here is still concise, as well as specific and arguable.  We can see that it is specific because the writer is mentioning (a) concrete ideas and (b) exact authors.  We can also gather the field (business) and the topic (management and employee turnover). The statement is arguable because the student goes beyond merely comparing; he or she draws conclusions from that comparison ("can reduce the expenses associated with employee turnover").

Making a Unique Argument

This thesis draft repeats the language of the writing prompt without making a unique argument:

Needs Improvement: The purpose of this essay is to monitor, assess, and evaluate an educational program for its strengths and weaknesses. Then, I will provide suggestions for improvement.

You can see here that the student has simply stated the paper's assignment, without articulating specifically how he or she will address it. The student can correct this error simply by phrasing the thesis statement as a specific answer to the assignment prompt.

Better: Through a series of student interviews, I found that Kennedy High School's antibullying program was ineffective. In order to address issues of conflict between students, I argue that Kennedy High School should embrace policies outlined by the California Department of Education (2010).

Words like "ineffective" and "argue" show here that the student has clearly thought through the assignment and analyzed the material; he or she is putting forth a specific and debatable position. The concrete information ("student interviews," "antibullying") further prepares the reader for the body of the paper and demonstrates how the student has addressed the assignment prompt without just restating that language.

Creating a Debate

This thesis statement includes only obvious fact or plot summary instead of argument:

Needs Improvement: Leadership is an important quality in nurse educators.

A good strategy to determine if your thesis statement is too broad (and therefore, not arguable) is to ask yourself, "Would a scholar in my field disagree with this point?" Here, we can see easily that no scholar is likely to argue that leadership is an unimportant quality in nurse educators.  The student needs to come up with a more arguable claim, and probably a narrower one; remember that a short paper needs a more focused topic than a dissertation.

Better: Roderick's (2009) theory of participatory leadership  is particularly appropriate to nurse educators working within the emergency medicine field, where students benefit most from collegial and kinesthetic learning.

Here, the student has identified a particular type of leadership ("participatory leadership"), narrowing the topic, and has made an arguable claim (this type of leadership is "appropriate" to a specific type of nurse educator). Conceivably, a scholar in the nursing field might disagree with this approach. The student's paper can now proceed, providing specific pieces of evidence to support the arguable central claim.

Choosing the Right Words

This thesis statement uses large or scholarly-sounding words that have no real substance:

Needs Improvement: Scholars should work to seize metacognitive outcomes by harnessing discipline-based networks to empower collaborative infrastructures.

There are many words in this sentence that may be buzzwords in the student's field or key terms taken from other texts, but together they do not communicate a clear, specific meaning. Sometimes students think scholarly writing means constructing complex sentences using special language, but actually it's usually a stronger choice to write clear, simple sentences. When in doubt, remember that your ideas should be complex, not your sentence structure.

Better: Ecologists should work to educate the U.S. public on conservation methods by making use of local and national green organizations to create a widespread communication plan.

Notice in the revision that the field is now clear (ecology), and the language has been made much more field-specific ("conservation methods," "green organizations"), so the reader is able to see concretely the ideas the student is communicating.

Leaving Room for Discussion

This thesis statement is not capable of development or advancement in the paper:

Needs Improvement: There are always alternatives to illegal drug use.

This sample thesis statement makes a claim, but it is not a claim that will sustain extended discussion. This claim is the type of claim that might be appropriate for the conclusion of a paper, but in the beginning of the paper, the student is left with nowhere to go. What further points can be made? If there are "always alternatives" to the problem the student is identifying, then why bother developing a paper around that claim? Ideally, a thesis statement should be complex enough to explore over the length of the entire paper.

Better: The most effective treatment plan for methamphetamine addiction may be a combination of pharmacological and cognitive therapy, as argued by Baker (2008), Smith (2009), and Xavier (2011).

In the revised thesis, you can see the student make a specific, debatable claim that has the potential to generate several pages' worth of discussion. When drafting a thesis statement, think about the questions your thesis statement will generate: What follow-up inquiries might a reader have? In the first example, there are almost no additional questions implied, but the revised example allows for a good deal more exploration.

Thesis Mad Libs

If you are having trouble getting started, try using the models below to generate a rough model of a thesis statement! These models are intended for drafting purposes only and should not appear in your final work.

• In this essay, I argue ____, using ______ to assert _____.
• While scholars have often argued ______, I argue______, because_______.
• Through an analysis of ______, I argue ______, which is important because_______.

Words to Avoid and to Embrace

When drafting your thesis statement, avoid words like explore, investigate, learn, compile, summarize , and explain to describe the main purpose of your paper. These words imply a paper that summarizes or "reports," rather than synthesizing and analyzing.

Instead of the terms above, try words like argue, critique, question , and interrogate . These more analytical words may help you begin strongly, by articulating a specific, critical, scholarly position.

Read Kayla's blog post for tips on taking a stand in a well-crafted thesis statement.

Related Resources

Didn't find what you need? Email us at [email protected] .

• Previous Page: Introductions
• Next Page: Conclusions
• Office of Student Disability Services

Walden Resources

Departments.

• Academic Residencies
• Academic Skills
• Career Planning and Development
• Customer Care Team
• Field Experience
• Military Services
• Student Success Advising
• Writing Skills

Centers and Offices

• Center for Social Change
• Office of Academic Support and Instructional Services
• Office of Degree Acceleration
• Office of Research and Doctoral Services
• Office of Student Affairs

Student Resources

• Doctoral Writing Assessment
• Form & Style Review
• Quick Answers
• ScholarWorks
• SKIL Courses and Workshops
• Walden Bookstore
• Walden Catalog & Student Handbook
• Student Safety/Title IX
• Legal & Consumer Information
• Website Terms and Conditions
• Cookie Policy
• Accessibility
• Accreditation
• State Authorization
• Net Price Calculator
• Contact Walden

Walden University is a member of Adtalem Global Education, Inc. www.adtalem.com Walden University is certified to operate by SCHEV © 2024 Walden University LLC. All rights reserved.

Library Research 101: Start Your Research

• Articles--what are they and where are they?
• Books--what are they and where are they?
• How do I choose a topic?
• How do I write a research question?

The thesis statement

• How do I cite?
• Glossary: Library terms

What is a thesis statement ?

• A thesis statement comes at the beginning of your paper. 
• It is a statement that answers your research question.
• The statement is supported throughout your paper with examples and evidence.

What makes a good thesis statement?

• It takes a position, or advances an opinion.
• It is specific, not too broad, but not too narrow.
• It is an arguable statement; there is room for discussion or disagreement.
• It provides focus and generates interest in the reader.
• << Previous: How do I write a research question?
• Next: How do I cite? >>
• Last Updated: Feb 8, 2024 9:04 AM
• URL: https://libguides.library.umaine.edu/libraryresearch101

5729 Fogler Library · University of Maine · Orono, ME 04469-5729 | (207) 581-1673

What are your chances of acceptance?

Calculate for all schools, your chance of acceptance.

Your chancing factors

Extracurriculars.

How to Write a Strong Thesis Statement: 4 Steps + Examples

What’s Covered:

What is the purpose of a thesis statement, writing a good thesis statement: 4 steps, common pitfalls to avoid, where to get your essay edited for free.

When you set out to write an essay, there has to be some kind of point to it, right? Otherwise, your essay would just be a big jumble of word salad that makes absolutely no sense. An essay needs a central point that ties into everything else. That main point is called a thesis statement, and it’s the core of any essay or research paper.

You may hear about Master degree candidates writing a thesis, and that is an entire paper–not to be confused with the thesis statement, which is typically one sentence that contains your paper’s focus. 

Read on to learn more about thesis statements and how to write them. We’ve also included some solid examples for you to reference.

Typically the last sentence of your introductory paragraph, the thesis statement serves as the roadmap for your essay. When your reader gets to the thesis statement, they should have a clear outline of your main point, as well as the information you’ll be presenting in order to either prove or support your point. 

The thesis statement should not be confused for a topic sentence , which is the first sentence of every paragraph in your essay. If you need help writing topic sentences, numerous resources are available. Topic sentences should go along with your thesis statement, though.

Since the thesis statement is the most important sentence of your entire essay or paper, it’s imperative that you get this part right. Otherwise, your paper will not have a good flow and will seem disjointed. That’s why it’s vital not to rush through developing one. It’s a methodical process with steps that you need to follow in order to create the best thesis statement possible.

Step 1: Decide what kind of paper you’re writing

When you’re assigned an essay, there are several different types you may get. Argumentative essays are designed to get the reader to agree with you on a topic. Informative or expository essays present information to the reader. Analytical essays offer up a point and then expand on it by analyzing relevant information. Thesis statements can look and sound different based on the type of paper you’re writing. For example:

• Argumentative: The United States needs a viable third political party to decrease bipartisanship, increase options, and help reduce corruption in government.
• Informative: The Libertarian party has thrown off elections before by gaining enough support in states to get on the ballot and by taking away crucial votes from candidates.
• Analytical: An analysis of past presidential elections shows that while third party votes may have been the minority, they did affect the outcome of the elections in 2020, 2016, and beyond.

Step 2: Figure out what point you want to make

Once you know what type of paper you’re writing, you then need to figure out the point you want to make with your thesis statement, and subsequently, your paper. In other words, you need to decide to answer a question about something, such as:

• What impact did reality TV have on American society?
• How has the musical Hamilton affected perception of American history?
• Why do I want to major in [chosen major here]?

If you have an argumentative essay, then you will be writing about an opinion. To make it easier, you may want to choose an opinion that you feel passionate about so that you’re writing about something that interests you. For example, if you have an interest in preserving the environment, you may want to choose a topic that relates to that. 

If you’re writing your college essay and they ask why you want to attend that school, you may want to have a main point and back it up with information, something along the lines of:

“Attending Harvard University would benefit me both academically and professionally, as it would give me a strong knowledge base upon which to build my career, develop my network, and hopefully give me an advantage in my chosen field.”

Step 3: Determine what information you’ll use to back up your point

Once you have the point you want to make, you need to figure out how you plan to back it up throughout the rest of your essay. Without this information, it will be hard to either prove or argue the main point of your thesis statement. If you decide to write about the Hamilton example, you may decide to address any falsehoods that the writer put into the musical, such as:

“The musical Hamilton, while accurate in many ways, leaves out key parts of American history, presents a nationalist view of founding fathers, and downplays the racism of the times.”

Once you’ve written your initial working thesis statement, you’ll then need to get information to back that up. For example, the musical completely leaves out Benjamin Franklin, portrays the founding fathers in a nationalist way that is too complimentary, and shows Hamilton as a staunch abolitionist despite the fact that his family likely did own slaves. 

Step 4: Revise and refine your thesis statement before you start writing

Read through your thesis statement several times before you begin to compose your full essay. You need to make sure the statement is ironclad, since it is the foundation of the entire paper. Edit it or have a peer review it for you to make sure everything makes sense and that you feel like you can truly write a paper on the topic. Once you’ve done that, you can then begin writing your paper.

When writing a thesis statement, there are some common pitfalls you should avoid so that your paper can be as solid as possible. Make sure you always edit the thesis statement before you do anything else. You also want to ensure that the thesis statement is clear and concise. Don’t make your reader hunt for your point. Finally, put your thesis statement at the end of the first paragraph and have your introduction flow toward that statement. Your reader will expect to find your statement in its traditional spot.

If you’re having trouble getting started, or need some guidance on your essay, there are tools available that can help you. CollegeVine offers a free peer essay review tool where one of your peers can read through your essay and provide you with valuable feedback. Getting essay feedback from a peer can help you wow your instructor or college admissions officer with an impactful essay that effectively illustrates your point.

Related CollegeVine Blog Posts

BibGuru Blog

Be more productive in school

• Citation Styles

How to write a thesis statement for a research paper

The thesis statement is the central argument of your research paper makes and serves as a roadmap for the entire essay. Therefore, writing a strong thesis statement is essential for crafting a successful research paper—but it can also be one of the most challenging aspects of the writing process. In this post, we discuss strategies for creating a quality thesis statement.

What is a thesis statement?

A thesis statement is the main argument of an academic essay or research paper . It states directly what you plan to argue in the paper.

A thesis statement is typically a single sentence, but it can be longer depending on the length and type of paper that you’re writing.

How to write a good thesis statement

In this section, we outline five key tips for writing a good thesis statement. If you’re struggling to come up with a research topic or a thesis, consider asking your instructor or a librarian for additional assistance.

1. Start with a question

A good thesis statement should be an answer to a research question. Start by asking a question about your topic that you want to address in your paper. This will help you focus your research and give your paper direction. The thesis statement should be a concise answer to this question.

Your research question should not be too broad or narrow. If the question is too broad, you may not be able to answer it effectively. If the question is too narrow, you may not have enough material to write a complete research paper. As a result, it’s important to strike a balance between a question that is too broad and one that is too narrow.

Thesis statements always respond to an existing scholarly conversation; so, formulate your research question and thesis in response to a current debate. Are there gaps in the current research? Where might your argument intervene?

2. Be specific

Your thesis statement should be specific and precise. It should clearly state the main point that you will be arguing in your paper. Avoid vague or general statements that are not arguable (see below). The more specific your thesis statement is, the easier it will be to write your paper.

To make your thesis statement specific, focus on a particular aspect of your topic. For example, if your topic is about the effects of social media on mental health, you can focus on a specific age group or a particular social media platform.

3. Make it debatable

A good thesis statement must be debatable (otherwise, it’s not actually an argument). It should present an argument that can be supported with evidence. Avoid statements that are purely factual or descriptive. Your thesis statement should take a position on a topic and argue for its validity.

4. Use strong language

Use strong, definitive language in your thesis statement. Try to avoid sounding tentative or uncertain. Your thesis statement should be confident and assertive, and it should clearly state your position on the topic.

It’s a myth that you can’t use “I” in an academic paper, so consider constructing your thesis statement in the form of “I argue that…” This conveys a strong and firm position.

To help make your thesis more assertive, avoid using vague language. For example, instead of writing, "I think social media has a negative impact on mental health," you might write, "Social media has a negative impact on mental health" or “I argue that social media has a negative impact on mental health.”

5. Revise and refine

Finally, remember that your thesis statement is not set in stone. You may need to revise, and refine, it as you conduct your research and write your paper. Don't be afraid to make changes to your thesis statement as you go along.

As you conduct your research and write your paper, you may discover new information that requires you to adjust your thesis statement. Or, as you work through a second draft, you might find that you’ve actually argued something different than you intended. Therefore, it is important to be flexible and open to making changes to your thesis statement.

The bottom line

Remember that your thesis statement is the foundation of your paper, so it's important to spend time crafting it carefully. A solid thesis enables you to write a research paper that effectively communicates your argument to your readers.

Frequently Asked Questions about how to create a thesis statement

Here is an example of a thesis statement: “I argue that social media has a negative impact on mental health.”

A good thesis statement should be an answer to a research question. Start by asking a question about your topic that you want to answer in your paper. The thesis statement should be a concise answer to this question.

Start your thesis statement with the words, “I argue that…” This conveys a strong and firm position.

A strong thesis is a direct, 1-2 sentence statement of your paper’s main argument. Good thesis statements are specific, balanced, and formed in response to an ongoing scholarly conversation.

Make your life easier with our productivity and writing resources.

For students and teachers.

Canvas | University | Ask a Librarian

• Library Homepage
• Arrendale Library

Writing a Research Paper

Writing a thesis statement.

• About This Guide
• Types of Research Papers
• Choosing a Topic
• Gathering Research
• Journals and Magazines This link opens in a new window
• Creating an Outline
• Writing Your Paper
• Citing Resources
• Academic Integrity This link opens in a new window
• Contact Us!

 Call us at 706-776-0111

  Chat with a Librarian

  Send Us Email

  Library Hours

A thesis statement is a declarative sentence that asserts the position a paper will be taking. This statement should be both specific and arguable. Generally, the thesis statement will be placed at the end of the first paragraph of your paper. The remainder of your paper will support this thesis.

After you've landed on a satisfactory topic, your next step will be to solidify the position you would like to take and write a clear and succinct thesis statement which will lay the foundation for the rest of your paper.

For the sake of example, let's say that you've chosen to argue the merits of eating locally grown foods. You want to focus on the positive effects that this will have on one's health, the local economy, and on global ecology. You also want to dispel the myth that eating locally is more expensive, and therefore, the exclusive purview of the upper middle class.

An example of a thesis statement outlining your position might look like this:

The locavore movement that has gained popularity in the United States over the past several years offers a way to increase health, support the local economy, and promote global ecology by making some simple changes to the way that you and your family eat. Although frequently criticized for being far more expensive than eating factory-farmed foods, the truth is that the costs of home gardening and the prices for which you can purchase food at your local farmer's market are often far less expensive alternatives than buying from a chain grocer, not to mention safer and more nutritious.

• << Previous: Choosing a Topic
• Next: Gathering Research >>
• Last Updated: Jul 12, 2023 9:03 AM
• URL: https://library.piedmont.edu/research_paper
• Ebooks & Online Video
• New Materials
• Renew Checkouts
• Faculty Resources
• Friends of the Library
• Library Services
• Request Books from Demorest
• Our Mission
• Library History
• Ask a Librarian!
• Making Citations
• Working Online

Arrendale Library Piedmont University 706-776-0111

• Skip to main content
• Skip to ChatBot Assistant
• Academic Writing
• What is a Research Paper?
• Steps in Writing a Research Paper
• Critical Reading and Writing
• Punctuation
• Writing Exercises
• ELL/ESL Resources

Developing a Research Thesis

A research thesis has most of the same  thesis characteristics as a thesis for a non-research essay. The difference lies in the fact that you will be gathering information and evidence from appropriate, valid sources to support your perspective on a topic or stand on an issue. Yet although your sources provide information that informs your thesis, the thesis ideas should be your own, particular to your personal way of thinking about and analyzing a topic.

The thesis focuses your ideas and information for the research paper. Remember that word "focus." Student writers often make the mistake of forgetting the focus and making the research thesis far too broad in order to include too much research. Yet depth more than breadth is the hallmark of a sophisticated research paper.

Create a working thesis for the research paper by specifying and ordering your categories of information. For example, the following theses offer the writers' main arguments and focus their research by specifying and ordering the reasons for their stance:

• Competency-based management is practical, logical, and accessible to managers and workers.
• Workforce training in basic skills is now necessary because of the lower reading and writing levels of the workforce, the fact that a person now entering the workforce will change jobs many times, the shift in jobs from the manufacturing to the service sectors, and the more comprehensive, abstract nature of those service jobs.

As you can see, a research thesis is your proposed answer to your research question, which you finalize only after completing the research. (It's okay to modify and revise the working thesis as you research more about the topic or issue.)

Developing a good working thesis, just like developing a good research question (researchable: neither too broad nor too narrow) is an important research skill.

Need Assistance?

If you would like assistance with any type of writing assignment, learning coaches are available to assist you. Please contact Academic Support by emailing [email protected].

Questions or feedback about SUNY Empire's Writing Support?

Contact us at [email protected] .

Smart Cookies

They're not just in our classes – they help power our website. Cookies and similar tools allow us to better understand the experience of our visitors. By continuing to use this website, you consent to SUNY Empire State University's usage of cookies and similar technologies in accordance with the university's Privacy Notice and Cookies Policy .

• How to write a research paper

Last updated

11 January 2024

Reviewed by

With proper planning, knowledge, and framework, completing a research paper can be a fulfilling and exciting experience. 

Though it might initially sound slightly intimidating, this guide will help you embrace the challenge. 

By documenting your findings, you can inspire others and make a difference in your field. Here's how you can make your research paper unique and comprehensive.

• What is a research paper?

Research papers allow you to demonstrate your knowledge and understanding of a particular topic. These papers are usually lengthier and more detailed than typical essays, requiring deeper insight into the chosen topic.

To write a research paper, you must first choose a topic that interests you and is relevant to the field of study. Once you’ve selected your topic, gathering as many relevant resources as possible, including books, scholarly articles, credible websites, and other academic materials, is essential. You must then read and analyze these sources, summarizing their key points and identifying gaps in the current research.

You can formulate your ideas and opinions once you thoroughly understand the existing research. To get there might involve conducting original research, gathering data, or analyzing existing data sets. It could also involve presenting an original argument or interpretation of the existing research.

Writing a successful research paper involves presenting your findings clearly and engagingly, which might involve using charts, graphs, or other visual aids to present your data and using concise language to explain your findings. You must also ensure your paper adheres to relevant academic formatting guidelines, including proper citations and references.

Overall, writing a research paper requires a significant amount of time, effort, and attention to detail. However, it is also an enriching experience that allows you to delve deeply into a subject that interests you and contribute to the existing body of knowledge in your chosen field.

• How long should a research paper be?

Research papers are deep dives into a topic. Therefore, they tend to be longer pieces of work than essays or opinion pieces. 

However, a suitable length depends on the complexity of the topic and your level of expertise. For instance, are you a first-year college student or an experienced professional? 

Also, remember that the best research papers provide valuable information for the benefit of others. Therefore, the quality of information matters most, not necessarily the length. Being concise is valuable.

Following these best practice steps will help keep your process simple and productive:

1. Gaining a deep understanding of any expectations

Before diving into your intended topic or beginning the research phase, take some time to orient yourself. Suppose there’s a specific topic assigned to you. In that case, it’s essential to deeply understand the question and organize your planning and approach in response. Pay attention to the key requirements and ensure you align your writing accordingly. 

This preparation step entails

Deeply understanding the task or assignment

Being clear about the expected format and length

Familiarizing yourself with the citation and referencing requirements 

Understanding any defined limits for your research contribution

Where applicable, speaking to your professor or research supervisor for further clarification

2. Choose your research topic

Select a research topic that aligns with both your interests and available resources. Ideally, focus on a field where you possess significant experience and analytical skills. In crafting your research paper, it's crucial to go beyond summarizing existing data and contribute fresh insights to the chosen area.

Consider narrowing your focus to a specific aspect of the topic. For example, if exploring the link between technology and mental health, delve into how social media use during the pandemic impacts the well-being of college students. Conducting interviews and surveys with students could provide firsthand data and unique perspectives, adding substantial value to the existing knowledge.

When finalizing your topic, adhere to legal and ethical norms in the relevant area (this ensures the integrity of your research, protects participants' rights, upholds intellectual property standards, and ensures transparency and accountability). Following these principles not only maintains the credibility of your work but also builds trust within your academic or professional community.

For instance, in writing about medical research, consider legal and ethical norms, including patient confidentiality laws and informed consent requirements. Similarly, if analyzing user data on social media platforms, be mindful of data privacy regulations, ensuring compliance with laws governing personal information collection and use. Aligning with legal and ethical standards not only avoids potential issues but also underscores the responsible conduct of your research.

3. Gather preliminary research

Once you’ve landed on your topic, it’s time to explore it further. You’ll want to discover more about available resources and existing research relevant to your assignment at this stage. 

This exploratory phase is vital as you may discover issues with your original idea or realize you have insufficient resources to explore the topic effectively. This key bit of groundwork allows you to redirect your research topic in a different, more feasible, or more relevant direction if necessary. 

Spending ample time at this stage ensures you gather everything you need, learn as much as you can about the topic, and discover gaps where the topic has yet to be sufficiently covered, offering an opportunity to research it further. 

4. Define your research question

To produce a well-structured and focused paper, it is imperative to formulate a clear and precise research question that will guide your work. Your research question must be informed by the existing literature and tailored to the scope and objectives of your project. By refining your focus, you can produce a thoughtful and engaging paper that effectively communicates your ideas to your readers.

5. Write a thesis statement

A thesis statement is a one-to-two-sentence summary of your research paper's main argument or direction. It serves as an overall guide to summarize the overall intent of the research paper for you and anyone wanting to know more about the research.

A strong thesis statement is:

Concise and clear: Explain your case in simple sentences (avoid covering multiple ideas). It might help to think of this section as an elevator pitch.

Specific: Ensure that there is no ambiguity in your statement and that your summary covers the points argued in the paper.

Debatable: A thesis statement puts forward a specific argument––it is not merely a statement but a debatable point that can be analyzed and discussed.

Here are three thesis statement examples from different disciplines:

Psychology thesis example: "We're studying adults aged 25-40 to see if taking short breaks for mindfulness can help with stress. Our goal is to find practical ways to manage anxiety better."

Environmental science thesis example: "This research paper looks into how having more city parks might make the air cleaner and keep people healthier. I want to find out if more green spaces means breathing fewer carcinogens in big cities."

UX research thesis example: "This study focuses on improving mobile banking for older adults using ethnographic research, eye-tracking analysis, and interactive prototyping. We investigate the usefulness of eye-tracking analysis with older individuals, aiming to spark debate and offer fresh perspectives on UX design and digital inclusivity for the aging population."

6. Conduct in-depth research

A research paper doesn’t just include research that you’ve uncovered from other papers and studies but your fresh insights, too. You will seek to become an expert on your topic––understanding the nuances in the current leading theories. You will analyze existing research and add your thinking and discoveries.  It's crucial to conduct well-designed research that is rigorous, robust, and based on reliable sources. Suppose a research paper lacks evidence or is biased. In that case, it won't benefit the academic community or the general public. Therefore, examining the topic thoroughly and furthering its understanding through high-quality research is essential. That usually means conducting new research. Depending on the area under investigation, you may conduct surveys, interviews, diary studies, or observational research to uncover new insights or bolster current claims.

7. Determine supporting evidence

Not every piece of research you’ve discovered will be relevant to your research paper. It’s important to categorize the most meaningful evidence to include alongside your discoveries. It's important to include evidence that doesn't support your claims to avoid exclusion bias and ensure a fair research paper.

8. Write a research paper outline

Before diving in and writing the whole paper, start with an outline. It will help you to see if more research is needed, and it will provide a framework by which to write a more compelling paper. Your supervisor may even request an outline to approve before beginning to write the first draft of the full paper. An outline will include your topic, thesis statement, key headings, short summaries of the research, and your arguments.

9. Write your first draft

Once you feel confident about your outline and sources, it’s time to write your first draft. While penning a long piece of content can be intimidating, if you’ve laid the groundwork, you will have a structure to help you move steadily through each section. To keep up motivation and inspiration, it’s often best to keep the pace quick. Stopping for long periods can interrupt your flow and make jumping back in harder than writing when things are fresh in your mind.

10. Cite your sources correctly

It's always a good practice to give credit where it's due, and the same goes for citing any works that have influenced your paper. Building your arguments on credible references adds value and authenticity to your research. In the formatting guidelines section, you’ll find an overview of different citation styles (MLA, CMOS, or APA), which will help you meet any publishing or academic requirements and strengthen your paper's credibility. It is essential to follow the guidelines provided by your school or the publication you are submitting to ensure the accuracy and relevance of your citations.

11. Ensure your work is original

It is crucial to ensure the originality of your paper, as plagiarism can lead to serious consequences. To avoid plagiarism, you should use proper paraphrasing and quoting techniques. Paraphrasing is rewriting a text in your own words while maintaining the original meaning. Quoting involves directly citing the source. Giving credit to the original author or source is essential whenever you borrow their ideas or words. You can also use plagiarism detection tools such as Scribbr or Grammarly to check the originality of your paper. These tools compare your draft writing to a vast database of online sources. If you find any accidental plagiarism, you should correct it immediately by rephrasing or citing the source.

12. Revise, edit, and proofread

One of the essential qualities of excellent writers is their ability to understand the importance of editing and proofreading. Even though it's tempting to call it a day once you've finished your writing, editing your work can significantly improve its quality. It's natural to overlook the weaker areas when you've just finished writing a paper. Therefore, it's best to take a break of a day or two, or even up to a week, to refresh your mind. This way, you can return to your work with a new perspective. After some breathing room, you can spot any inconsistencies, spelling and grammar errors, typos, or missing citations and correct them. 

• The best research paper format 

The format of your research paper should align with the requirements set forth by your college, school, or target publication. 

There is no one “best” format, per se. Depending on the stated requirements, you may need to include the following elements:

Title page: The title page of a research paper typically includes the title, author's name, and institutional affiliation and may include additional information such as a course name or instructor's name. 

Table of contents: Include a table of contents to make it easy for readers to find specific sections of your paper.

Abstract: The abstract is a summary of the purpose of the paper.

Methods : In this section, describe the research methods used. This may include collecting data, conducting interviews, or doing field research.

Results: Summarize the conclusions you drew from your research in this section.

Discussion: In this section, discuss the implications of your research. Be sure to mention any significant limitations to your approach and suggest areas for further research.

Tables, charts, and illustrations: Use tables, charts, and illustrations to help convey your research findings and make them easier to understand.

Works cited or reference page: Include a works cited or reference page to give credit to the sources that you used to conduct your research.

Bibliography: Provide a list of all the sources you consulted while conducting your research.

Dedication and acknowledgments : Optionally, you may include a dedication and acknowledgments section to thank individuals who helped you with your research.

• General style and formatting guidelines

Formatting your research paper means you can submit it to your college, journal, or other publications in compliance with their criteria.

Research papers tend to follow the American Psychological Association (APA), Modern Language Association (MLA), or Chicago Manual of Style (CMOS) guidelines.

Here’s how each style guide is typically used:

Chicago Manual of Style (CMOS):

CMOS is a versatile style guide used for various types of writing. It's known for its flexibility and use in the humanities. CMOS provides guidelines for citations, formatting, and overall writing style. It allows for both footnotes and in-text citations, giving writers options based on their preferences or publication requirements.

American Psychological Association (APA):

APA is common in the social sciences. It’s hailed for its clarity and emphasis on precision. It has specific rules for citing sources, creating references, and formatting papers. APA style uses in-text citations with an accompanying reference list. It's designed to convey information efficiently and is widely used in academic and scientific writing.

Modern Language Association (MLA):

MLA is widely used in the humanities, especially literature and language studies. It emphasizes the author-page format for in-text citations and provides guidelines for creating a "Works Cited" page. MLA is known for its focus on the author's name and the literary works cited. It’s frequently used in disciplines that prioritize literary analysis and critical thinking.

To confirm you're using the latest style guide, check the official website or publisher's site for updates, consult academic resources, and verify the guide's publication date. Online platforms and educational resources may also provide summaries and alerts about any revisions or additions to the style guide.

Citing sources

When working on your research paper, it's important to cite the sources you used properly. Your citation style will guide you through this process. Generally, there are three parts to citing sources in your research paper: 

First, provide a brief citation in the body of your essay. This is also known as a parenthetical or in-text citation. 

Second, include a full citation in the Reference list at the end of your paper. Different types of citations include in-text citations, footnotes, and reference lists. 

In-text citations include the author's surname and the date of the citation. 

Footnotes appear at the bottom of each page of your research paper. They may also be summarized within a reference list at the end of the paper. 

A reference list includes all of the research used within the paper at the end of the document. It should include the author, date, paper title, and publisher listed in the order that aligns with your citation style.

10 research paper writing tips:

Following some best practices is essential to writing a research paper that contributes to your field of study and creates a positive impact.

These tactics will help you structure your argument effectively and ensure your work benefits others:

Clear and precise language:  Ensure your language is unambiguous. Use academic language appropriately, but keep it simple. Also, provide clear takeaways for your audience.

Effective idea separation:  Organize the vast amount of information and sources in your paper with paragraphs and titles. Create easily digestible sections for your readers to navigate through.

Compelling intro:  Craft an engaging introduction that captures your reader's interest. Hook your audience and motivate them to continue reading.

Thorough revision and editing:  Take the time to review and edit your paper comprehensively. Use tools like Grammarly to detect and correct small, overlooked errors.

Thesis precision:  Develop a clear and concise thesis statement that guides your paper. Ensure that your thesis aligns with your research's overall purpose and contribution.

Logical flow of ideas:  Maintain a logical progression throughout the paper. Use transitions effectively to connect different sections and maintain coherence.

Critical evaluation of sources:  Evaluate and critically assess the relevance and reliability of your sources. Ensure that your research is based on credible and up-to-date information.

Thematic consistency:  Maintain a consistent theme throughout the paper. Ensure that all sections contribute cohesively to the overall argument.

Relevant supporting evidence:  Provide concise and relevant evidence to support your arguments. Avoid unnecessary details that may distract from the main points.

Embrace counterarguments:  Acknowledge and address opposing views to strengthen your position. Show that you have considered alternative arguments in your field.

7 research tips 

If you want your paper to not only be well-written but also contribute to the progress of human knowledge, consider these tips to take your paper to the next level:

Selecting the appropriate topic: The topic you select should align with your area of expertise, comply with the requirements of your project, and have sufficient resources for a comprehensive investigation.

Use academic databases: Academic databases such as PubMed, Google Scholar, and JSTOR offer a wealth of research papers that can help you discover everything you need to know about your chosen topic.

Critically evaluate sources: It is important not to accept research findings at face value. Instead, it is crucial to critically analyze the information to avoid jumping to conclusions or overlooking important details. A well-written research paper requires a critical analysis with thorough reasoning to support claims.

Diversify your sources: Expand your research horizons by exploring a variety of sources beyond the standard databases. Utilize books, conference proceedings, and interviews to gather diverse perspectives and enrich your understanding of the topic.

Take detailed notes: Detailed note-taking is crucial during research and can help you form the outline and body of your paper.

Stay up on trends: Keep abreast of the latest developments in your field by regularly checking for recent publications. Subscribe to newsletters, follow relevant journals, and attend conferences to stay informed about emerging trends and advancements. 

Engage in peer review: Seek feedback from peers or mentors to ensure the rigor and validity of your research. Peer review helps identify potential weaknesses in your methodology and strengthens the overall credibility of your findings.

• The real-world impact of research papers

Writing a research paper is more than an academic or business exercise. The experience provides an opportunity to explore a subject in-depth, broaden one's understanding, and arrive at meaningful conclusions. With careful planning, dedication, and hard work, writing a research paper can be a fulfilling and enriching experience contributing to advancing knowledge.

How do I publish my research paper? 

Many academics wish to publish their research papers. While challenging, your paper might get traction if it covers new and well-written information. To publish your research paper, find a target publication, thoroughly read their guidelines, format your paper accordingly, and send it to them per their instructions. You may need to include a cover letter, too. After submission, your paper may be peer-reviewed by experts to assess its legitimacy, quality, originality, and methodology. Following review, you will be informed by the publication whether they have accepted or rejected your paper. 

What is a good opening sentence for a research paper? 

Beginning your research paper with a compelling introduction can ensure readers are interested in going further. A relevant quote, a compelling statistic, or a bold argument can start the paper and hook your reader. Remember, though, that the most important aspect of a research paper is the quality of the information––not necessarily your ability to storytell, so ensure anything you write aligns with your goals.

Research paper vs. a research proposal—what’s the difference?

While some may confuse research papers and proposals, they are different documents. 

A research proposal comes before a research paper. It is a detailed document that outlines an intended area of exploration. It includes the research topic, methodology, timeline, sources, and potential conclusions. Research proposals are often required when seeking approval to conduct research. 

A research paper is a summary of research findings. A research paper follows a structured format to present those findings and construct an argument or conclusion.

Get started today

Go from raw data to valuable insights with a flexible research platform

Editor’s picks

Last updated: 21 December 2023

Last updated: 16 December 2023

Last updated: 6 October 2023

Last updated: 5 March 2024

Last updated: 25 November 2023

Last updated: 15 February 2024

Last updated: 11 March 2024

Last updated: 12 December 2023

Last updated: 6 March 2024

Last updated: 10 April 2023

Last updated: 20 December 2023

Latest articles

Related topics.

• 10 research paper

Log in or sign up

Get started for free

To revisit this article, visit My Profile, then View saved stories .

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

Amanda Hoover

Students Are Likely Writing Millions of Papers With AI

Students have submitted more than 22 million papers that may have used generative AI in the past year, new data released by plagiarism detection company Turnitin shows.

A year ago, Turnitin rolled out an AI writing detection tool that was trained on its trove of papers written by students as well as other AI-generated texts. Since then, more than 200 million papers have been reviewed by the detector, predominantly written by high school and college students. Turnitin found that 11 percent may contain AI-written language in 20 percent of its content, with 3 percent of the total papers reviewed getting flagged for having 80 percent or more AI writing. (Turnitin is owned by Advance, which also owns Condé Nast, publisher of WIRED.) Turnitin says its detector has a false positive rate of less than 1 percent when analyzing full documents.

ChatGPT’s launch was met with knee-jerk fears that the English class essay would die . The chatbot can synthesize information and distill it near-instantly—but that doesn’t mean it always gets it right. Generative AI has been known to hallucinate , creating its own facts and citing academic references that don’t actually exist. Generative AI chatbots have also been caught spitting out biased text on gender and race . Despite those flaws, students have used chatbots for research, organizing ideas, and as a ghostwriter . Traces of chatbots have even been found in peer-reviewed, published academic writing .

Teachers understandably want to hold students accountable for using generative AI without permission or disclosure. But that requires a reliable way to prove AI was used in a given assignment. Instructors have tried at times to find their own solutions to detecting AI in writing, using messy, untested methods to enforce rules , and distressing students. Further complicating the issue, some teachers are even using generative AI in their grading processes.

Detecting the use of gen AI is tricky. It’s not as easy as flagging plagiarism, because generated text is still original text. Plus, there’s nuance to how students use gen AI; some may ask chatbots to write their papers for them in large chunks or in full, while others may use the tools as an aid or a brainstorm partner.

Students also aren't tempted by only ChatGPT and similar large language models. So-called word spinners are another type of AI software that rewrites text, and may make it less obvious to a teacher that work was plagiarized or generated by AI. Turnitin’s AI detector has also been updated to detect word spinners, says Annie Chechitelli, the company’s chief product officer. It can also flag work that was rewritten by services like spell checker Grammarly, which now has its own generative AI tool . As familiar software increasingly adds generative AI components, what students can and can’t use becomes more muddled.

Detection tools themselves have a risk of bias. English language learners may be more likely to set them off; a 2023 study found a 61.3 percent false positive rate when evaluating Test of English as a Foreign Language (TOEFL) exams with seven different AI detectors. The study did not examine Turnitin’s version. The company says it has trained its detector on writing from English language learners as well as native English speakers. A study published in October found that Turnitin was among the most accurate of 16 AI language detectors in a test that had the tool examine undergraduate papers and AI-generated papers.

Medea Giordano

Nena Farrell

Schools that use Turnitin had access to the AI detection software for a free pilot period, which ended at the start of this year. Chechitelli says a majority of the service’s clients have opted to purchase the AI detection. But the risks of false positives and bias against English learners have led some universities to ditch the tools for now. Montclair State University in New Jersey announced in November that it would pause use of Turnitin’s AI detector. Vanderbilt University and Northwestern University did the same last summer.

“This is hard. I understand why people want a tool,” says Emily Isaacs, executive director of the Office of Faculty Excellence at Montclair State. But Isaacs says the university is concerned about potentially biased results from AI detectors, as well as the fact that the tools can’t provide confirmation the way they can with plagiarism. Plus, Montclair State doesn’t want to put a blanket ban on AI, which will have some place in academia. With time and more trust in the tools, the policies could change. “It’s not a forever decision, it’s a now decision,” Isaacs says.

Chechitelli says the Turnitin tool shouldn’t be the only consideration in passing or failing a student. Instead, it’s a chance for teachers to start conversations with students that touch on all of the nuance in using generative AI. “People don’t really know where that line should be,” she says.

You Might Also Like …

In your inbox: The best and weirdest stories from WIRED’s archive

Jeffrey Epstein’s island visitors exposed by data broker

8 Google employees invented modern AI. Here’s the inside story

The crypto fraud kingpin who almost got away

Listen up! These are the best podcasts , no matter what you’re into

Stephen Ornes

Will Knight

Estelle Erasmus

Kate Knibbs

Steven Levy

Matt Burgess

Reece Rogers

Search code, repositories, users, issues, pull requests...

Provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications

[Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications

Event-AHU/Mamba_State_Space_Model_Paper_List

Folders and files, repository files navigation, mamba_state_space_model_paper_list.

Paper list for State-Space-Model and its Applications

We appreciate any useful suggestions for improvement of this paper list or survey from peers. Please raise issues or send an email to [email protected] . Thanks for your cooperation!

💥 update log.

• [2024.04.15] We release the first version of the survey on state space model [ arXiv ]

Thesis & Surveys

Modeling sequences with structured state spaces , Responsibility: Albert Gu, Publication: [Stanford, California] : [Stanford University], 2023 [ Thesis (330 pages) ] [ PDF ]

State Space Model for New-Generation Network Alternative to Transformers: A Survey , Xiao Wang, Shiao Wang, Yuhe Ding, Yuehang Li, Wentao Wu, Yao Rong, Weizhe Kong, Ju Huang, Shihao Li, Haoxiang Yang, Ziwen Wang, Bo Jiang, Chenglong Li, Yaowei Wang, Yonghong Tian, Jin Tang, 2024 [ PDF ] [ arXiv ]

CU-Mamba: Selective State Space Models with Channel Learning for Image Restoration , arXiv:2404.11778, Rui Deng, Tianpei Gu [ Paper ]

State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend , Fei Cui, Jiaojiao Fang, Xiaojiang Wu, Zelong Lai, Mengke Yang, Menghan Jia, Guizhong Liu [ Paper ]

Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion , Xinghan Wang, Zixi Kang, Yadong Mu, arXiv:2404.11375 [ Paper ]

HumMUSS: Human Motion Understanding using State Space Models , Arnab Kumar Mondal, Stefano Alletto, Denis Tome, CVPR 2024, arXiv:2404.10880 [ Paper ]

HSIDMamba: Exploring Bidirectional State-Space Models for Hyperspectral Denoising , Yang Liu, Jiahua Xiao, Yu Guo, Peilin Jiang, Haiwei Yang, Fei Wang [ Paper ]

FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba , Xinyu Xie, Yawen Cui, Chio-In Ieong, Tao Tan, Xiaozhi Zhang, Xubin Zheng, Zitong Yu [ Paper ] [ Code ]

FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining , Zou Zhen, Yu Hu, Zhao Feng [ Paper ]

A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion , Zihan Cao, Xiao Wu, Liang-Jian Deng, Yu Zhong [ Paper ]

Fusion-Mamba for Cross-modality Object Detection , arXiv:2404.09146, Wenhao Dong, Haodong Zhu, Shaohui Lin, Xiaoyan Luo, Yunhang Shen, Xuhui Liu, Juan Zhang, Guodong Guo, Baochang Zhang [ Paper ]

" Linear recurrent units for sequential recommendation. " Yue, Zhenrui, et al. Proceedings of the 17th ACM International Conference on Web Search and Data Mining. 2024. [ Paper ] [ Code ]

State-Space Modeling of Shape-constrained Functional Time Series , Daichi Hiraki, Yasuyuki Hamura, Kaoru Irie, Shonosuke Sugasawa, arXiv:2404.07586 [ Paper ]

HGRN2: Gated Linear RNNs with State Expansion , Zhen Qin, Songlin Yang, Weixuan Sun, Xuyang Shen, Dong Li, Weigao Sun, Yiran Zhong, arXiv:2404.07904 [ Paper ] [ Code ]

MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion , Zhe Li, Haiwei Pan, Kejia Zhang, Yuhua Wang, Fengming Yu, arXiv:2404.08406 [ Paper ]

SpectralMamba: Efficient Mamba for Hyperspectral Image Classification , Jing Yao, Danfeng Hong, Chenyu Li, Jocelyn Chanussot, arXiv:2404.08489 [ Paper ] [ Code ]

SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival Prediction , Ying Chen, Jiajing Xie, Yuxiang Lin, Yuhang Song, Wenxian Yang, Rongshan Yu, arXiv:2404.08027 [ Paper ]

[2024_143] FusionMamba: Efficient Image Fusion with State Space Model , Siran Peng, Xiangyu Zhu, Haoyu Deng, Zhen Lei, Liang-Jian Deng [ Paper ]

[2024_142] DGMamba: Domain Generalization via Generalized State Space Model , Shaocong Long, Qianyu Zhou, Xiangtai Li, Xuequan Lu, Chenhao Ying, Yuan Luo, Lizhuang Ma, Shuicheng Yan [ Paper ]

[2024_141] ViM-UNet: Vision Mamba for Biomedical Segmentation , Anwai Archit, Constantin Pape [ Paper ] [ Code ]

[2024_140] Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos , Soumyabrata Chaudhuri, Saumik Bhattacharya [ Paper ]

[2024_139] MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection , Haoyang He, Yuhu Bai, Jiangning Zhang, Qingdong He, Hongxu Chen, Zhenye Gan, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Lei Xie [ Paper ]

[2024_138] 3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion , Yixuan Li, Weidong Yang, Ben Fei [ Paper ]

[2024_137] RhythmMamba: Fast Remote Physiological Measurement with Arbitrary Length Videos , Bochao Zou, Zizheng Guo, Xiaocheng Hu, Huimin Ma [ Paper ] [ Code ]

[2024_136] VMambaMorph: a Visual Mamba-based Framework with Cross-Scan Module for Deformable 3D Image Registration , Ziyang Wang, Jian-Qing Zheng, Chao Ma, Tao Guo [ Paper ]

[2024_135] 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering , Qingyuan Zhou, Weidong Yang, Ben Fei, Jingyi Xu, Rui Zhang, Keyi Liu, Yeqi Luo, Ying He [ Paper ]

[2024_134] Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation , Zifu Wan, Yuhao Wang, Silong Yong, Pingping Zhang, Simon Stepputtis, Katia Sycara, Yaqi Xie [ Paper ] [ Code ]

[2024_133] xT: Nested Tokenization for Larger Context in Large Images , Ritwik Gupta, Shufan Li, Tyler Zhu, Jitendra Malik, Trevor Darrell, Karttikeya Mangalam [ Paper ] [ Code ]

[2024_132] Locating and Editing Factual Associations in Mamba , Arnab Sen Sharma, David Atkinson, David Bau [ Paper ]

[2024_131] InsectMamba: Insect Pest Classification with State Space Model , Qianning Wang, Chenglin Wang, Zhixin Lai, Yucheng Zhou [ Paper ]

[2024_130] ChangeMamba: Remote Sensing Change Detection with Spatio-Temporal State Space Model , Hongruixuan Chen, Jian Song, Chengxi Han, Junshi Xia, Naoto Yokoya [ Paper ] [ Code ]

[2024_129] RS-Mamba for Large Remote Sensing Image Dense Prediction , Sijie Zhao, Hao Chen, Xueliang Zhang, Pengfeng Xiao, Lei Bai, Wanli Ouyang [ Paper ] [ Code ]

[2024_128] RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic Segmentation , Xianping Ma, Xiaokang Zhang, Man-On Pun [ Paper ] [ Code ]

[2024_127] SPMamba: State-space model is all you need in speech separation , Kai Li, Guo Chen [ Paper ]

[2024_126] On the reduction of Linear Parameter-Varying State-Space models , E. Javier Olucha, Bogoljub Terzin, Amritam Das, Roland Tóth [ Paper ]

[2024_125] Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model , Qinfeng Zhu, Yuanzhi Cai, Yuan Fang, Yihan Yang, Cheng Chen, Lei Fan, Anh Nguyen [ Paper ] [ Code ]

[2024_124] T-Mamba: Frequency-Enhanced Gated Long-Range Dependency for Tooth 3D CBCT Segmentation , Jing Hao, Lei He, Kuo Feng Hung [ Paper ] [ Code ]

[2024_123] Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces , Toshihiro Ota [ Paper ]

[2024_122] RankMamba, Benchmarking Mamba's Document Ranking Performance in the Era of Transformers , Zhichao Xu [ Paper ] [ Code ]

[2024_121] SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding , Wenrui Li, Xiaopeng Hong, Xiaopeng Fan [ Paper ]

[2024_120] HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification , Judy X Yang, Jun Zhou, Jing Wang, Hui Tian, Alan Wee Chung Liew [ Paper ] [ Code ]

[2024_119] HARMamba: Efficient Wearable Sensor Human Activity Recognition Based on Bidirectional Selective SSM , Shuangjian Li, Tao Zhu, Furong Duan, Liming Chen, Huansheng Ning, Yaping Wan [ Paper ]

[2024_118] UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation , Renkai Wu, Yinghao Liu, Pengchen Liang, Qing Chang [ Paper ] [ Code ]

[2024_117] MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection , Ali Behrouz, Michele Santacatterina, Ramin Zabih [ Paper ]

[2024_116] Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation , Xilin Jiang, Cong Han, Nima Mesgarani [ Paper ]

[2024_115] STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model , Lincan Li, Hanchen Wang, Wenjie Zhang, Adelle Coster [ Paper ]

[2024_114] Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference , Han Zhao, Min Zhang, Wei Zhao, Pengxiang Ding, Siteng Huang, Donglin Wang [ Paper ]

[2024_113] Music to Dance as Language Translation using Sequence Models , André Correia, Luís A. Alexandre [ Paper ] [ Code ]

[2024_112] CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification , Guangqian Yang, Kangrui Du, Zhihan Yang, Ye Du, Yongping Zheng, Shujun Wang [ Paper ]

[2024_111] Proprioception Is All You Need: Terrain Classification for Boreal Forests , Damien LaRocque, William Guimont-Martin, David-Alexandre Duclos, Philippe Giguère, François Pomerleau [ Paper ]

[2024_110] ReMamber: Referring Image Segmentation with Mamba Twister , Yuhuan Yang, Chaofan Ma, Jiangchao Yao, Zhun Zhong, Ya Zhang, Yanfeng Wang [ Paper ]

[2024_109] Mechanistic Design and Scaling of Hybrid Architectures , Michael Poli, Armin W Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christopher Ré, Ce Zhang, Stefano Massaroli [ Paper ]

[2024_108] Model order reduction of deep structured state-space models: A system-theoretic approach , Marco Forgione, Manas Mejari, Dario Piga

[2024_107] Modeling Analog Dynamic Range Compressors using Deep Learning and State-space Models , Hanzhi Yin, Gang Cheng, Christian J. Steinmetz, Ruibin Yuan, Richard M. Stern, Roger B. Dannenberg [ Paper ]

[2024_106] Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation , Jiyuan Yang, Yuanzi Li, Jingyu Zhao, Hanbing Wang, Muyang Ma, Jun Ma, Zhaochun Ren, Mengqi Zhang, Xin Xin, Zhumin Chen, Pengjie Ren [ Paper ] [ Code ]

[2024_105] State Space Models as Foundation Models: A Control Theoretic Overview , Carmen Amo Alonso, Jerome Sieber, Melanie N. Zeilinger [ Paper ]

[2024_104] Serpent: Scalable and Efficient Image Restoration via Multi-scale Structured State Space Models , Mohammad Shahab Sepehri, Zalan Fabian, Mahdi Soltanolkotabi [ Paper ]

[2024_103] Jamba: A Hybrid Transformer-Mamba Language Model , Opher Lieber, Barak Lenz, Hofit Bata, Gal Cohen, Jhonathan Osin, Itay Dalmedigos, Erez Safahi, Shaked Meirom, Yonatan Belinkov, Shai Shalev-Shwartz, Omri Abend, Raz Alon, Tomer Asida, Amir Bergman, Roman Glozman, Michael Gokhman, Avashalom Manevich, Nir Ratner, Noam Rozen, Erez Shwartz, Mor Zusman, Yoav Shoham [ Paper ] [ Website ] [ Huggingface ]

[2024_102] Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction , Qiuhong Shen, Xuanyu Yi, Zike Wu, Pan Zhou, Hanwang Zhang, Shuicheng Yan, Xinchao Wang [ Paper ]

[2024_101] RSMamba: Remote Sensing Image Classification with State Space Model , [ Project ] [ Paper ] [ Code ]

[2024_100] Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentation , Hao Tang, Lianglun Cheng, Guoheng Huang, Zhengguang Tan, Junhao Lu, Kaihong Wu [ Paper ]

[2024_099] PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition , Chenhongyi Yang, Zehui Chen, Miguel Espinosa, Linus Ericsson, Zhenyu Wang, Jiaming Liu, Elliot J. Crowley [ Paper ] [ Code ]

[2024_098] Integrating Mamba Sequence Model and Hierarchical Upsampling Network for Accurate Semantic Segmentation of Multiple Sclerosis Legion , Kazi Shahriar Sanjid, Md. Tanzim Hossain, Md. Shakib Shahariar Junayed, Dr. Mohammad Monir Uddin [ Paper ]

[2024_097] VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting , Yujin Tang, Peijie Dong, Zhenheng Tang, Xiaowen Chu, Junwei Liang [ Paper ] [ Code ]

[2024_096] SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series , Badri N. Patro, Vijay S. Agneeswaran [ Paper ] [ Code ]

[2024_095] Repeat After Me: Transformers are Better than State Space Models at Copying , Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach [ Paper ]

[2024_094] H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation , Renkai Wu, Yinghao Liu, Pengchen Liang, Qing Chang [ Paper ] [ Code ]

[2024_093] VL-Mamba: Exploring State Space Models for Multimodal Learning , Yanyuan Qiao, Zheng Yu, Longteng Guo, Sihan Chen, Zijia Zhao, Mingzhen Sun, Qi Wu, Jing Liu [ Paper ] [ Project ] [ Code ]

[2024_092] ProMamba: Prompt-Mamba for polyp segmentation , Jianhao Xie, Ruofan Liao, Ziang Zhang, Sida Yi, Yuesheng Zhu, Guibo Luo [ Paper ]

[2024_091] ZigMa: Zigzag Mamba Diffusion Model , Vincent Tao Hu, Stefan Andreas Baumann, Ming Gui, Olga Grebenkova, Pingchuan Ma, Johannes Fischer, Bjorn Ommer [ Paper ] [ Code ]

[2024_090] On the low-shot transferability of [V]-Mamba , Diganta Misra, Jay Gala, Antonio Orvieto [ Paper ]

[2024_089] Is Mamba Effective for Time Series Forecasting? Zihan Wang, Fanheng Kong, Shi Feng, Ming Wang, Han Zhao, Daling Wang, Yifei Zhang [ Paper ] [ Code ]

[2024_088] VmambaIR: Visual State Space Model for Image Restoration , Yuan Shi, Bin Xia, Xiaoyu Jin, Xing Wang, Tianyu Zhao, Xin Xia, Xuefeng Xiao, Wenming Yang [ Paper ]

[2024_087] Understanding Robustness of Visual State Space Models for Image Classification , Chengbin Du, Yanxi Li, Chang Xu [ Paper ]

[2024_086] Regularization-Based Efficient Continual Learning in Deep State-Space Models , Yuanhang Zhang, Zhidi Lin, Yiyong Sun, Feng Yin, Carsten Fritsche [ Paper ]

[2024_085] TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting , Md Atik Ahamed, Qiang Cheng [ Paper ] [ Code ]

[2024_084] EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba , Xiaohuan Pei, Tao Huang, Chang Xu [ Paper ] [ Code ]

[2024_083] MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models , Zunnan Xu, Yukang Lin, Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang, Xiu Li [ Paper ]

[2024_082] LocalMamba: Visual State Space Model with Windowed Selective Scan , Tao Huang, Xiaohuan Pei, Shan You, Fei Wang, Chen Qian, Chang Xu [ Paper ] [ Code ]

[2024_081] VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation , Mingya Zhang, Yue Yu, Limei Gu, Tingsheng Lin, Xianping Tao [ Paper ] [ Code ]

[2024_080] Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding , Guo Chen, Yifei Huang, Jilan Xu, Baoqi Pei, Zhe Chen, Zhiqi Li, Jiahao Wang, Kunchang Li, Tong Lu, Limin Wang [ Paper ] [ Code ]

[2024_079] Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling , Raunaq Bhirangi, Chenyu Wang, Venkatesh Pattabiraman, Carmel Majidi, Abhinav Gupta, Tess Hellebrekers, Lerrel Pinto [ Paper ]

[2024_078] MambaStock: Selective state space model for stock prediction , Zhuangwei Shi [ Paper ] [ Code ]

[2024_077] Simple linear attention language models balance the recall-throughput tradeoff , Simran Arora, Sabri Eyuboglu, Michael Zhang, Aman Timalsina, Silas Alberti, Dylan Zinsley, James Zou, Atri Rudra, Christopher Ré [ Paper ]

[2024_076] LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation , Weibin Liao, Yinghao Zhu, Xinyuan Wang, Chengwei Pan, Yasha Wang, Liantao Ma [ Paper ] [ Code ]

[2024_075] Motion-Guided Dual-Camera Tracker for Low-Cost Skill Evaluation of Gastric Endoscopy , Yuelin Zhang, Wanquan Yan, Kim Yan, Chun Ping Lam, Yufu Qiu, Pengyu Zheng, Raymond Shing-Yan Tang, Shing Shin Cheng [ Paper ]

[2024_074] Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling , Yair Schiff, Chia-Hsiang Kao, Aaron Gokaslan, Tri Dao, Albert Gu, Volodymyr Kuleshov [ Paper ]

[2024_073] MD-Dose: A Diffusion Model based on the Mamba for Radiotherapy Dose Prediction , Linjie Fu, Xia Li, Xiuding Cai, Yingkai Wang, Xueyao Wang, Yali Shen, Yu Yao [ Paper ]

[2024_072] Activating Wider Areas in Image Super-Resolution , Cheng Cheng, Hang Wang, Hongbin Sun [ Paper ]

[2024_071] Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers , Changsheng Quan, Xiaofei Li [ Paper ]

[2024_070] A multi-cohort study on prediction of acute brain dysfunction states using selective state space models , Brandon Silva, Miguel Contreras, Sabyasachi Bandyopadhyay, Yuanfang Ren, Ziyuan Guan, Jeremy Balch, Kia Khezeli, Tezcan Ozrazgat Baslanti, Ben Shickel, Azra Bihorac, Parisa Rashidi [ Paper ]

[2024_069] The pitfalls of next-token prediction , Gregor Bachmann, Vaishnavh Nagarajan [ Paper ] [ Code ]

[2024_068] Large Window-based Mamba UNet for Medical Image Segmentation: Beyond Convolution and Self-attention , Jinhong Wang, Jintai Chen, Danny Chen, Jian Wu [ Paper ] [ Code ]

[2024_067] Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSM , Zeyu Zhang, Akide Liu, Ian Reid, Richard Hartley, Bohan Zhuang, Hao Tang [ Paper ] [ Project ] [ Code ]

[2024_066] ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes , Zhichao Yang, Avijit Mitra, Sunjae Kwon, Hong Yu [ Paper ] [ Code ]

[2024_065] MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology , Shu Yang, Yihui Wang, Hao Chen [ Paper ] [ Code ]

[2024_064] Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy , Jiuming Liu, Ruiji Yu, Yian Wang, Yu Zheng, Tianchen Deng, Weicai Ye, Hesheng Wang [ Paper ] [ Code ]

[2024_063] VideoMamba: State Space Model for Efficient Video Understanding , Kunchang Li, Xinhao Li, Yi Wang, Yinan He, Yali Wang, Limin Wang, Yu Qiao [ Paper ] [ Code ]

[2024_062] MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models , Zijie Fang, Yifeng Wang, Zhi Wang, Jian Zhang, Xiangyang Ji, Yongbing Zhang [ Paper ]

[2024_061] Video Diffusion State Space Models , Zhengcong Fei, Mingyuan Fan, Changqian Yu, Jusnshi Huang, [ Paper ] [ Code ]

[2024_060] Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models , Chengkai Liu, Jianghao Lin, Jianling Wang, Hanzhou Liu, James Caverlee [ Paper ]

[2024_059] MedMamba: Vision Mamba for Medical Image Classification , Yubiao Yue, Zhenzhang Li [ Paper ] [ Code ]

[2024_058] Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models , Soham De, Samuel L. Smith, Anushan Fernando, Aleksandar Botev, George Cristian-Muraru, Albert Gu, Ruba Haroun, Leonard Berrada, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, Arnaud Doucet, David Budden, Yee Whye Teh, Razvan Pascanu, Nando De Freitas, Caglar Gulcehre [ Paper ]

[2024_057] Gated Linear Attention Transformers with Hardware-Efficient Training , Songlin Yang, Bailin Wang, Yikang Shen, Rameswar Panda, Yoon Kim [ Paper ] [ Code ]

[2024_056] DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models , [ Paper ] [ Code ]

[2024_055] The Hidden Attention of Mamba Models , [ Paper ] [ Code ]

[2024_054] MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection , Tianxiang Chen, Zhentao Tan, Tao Gong, Qi Chu, Yue Wu, Bin Liu, Jieping Ye, Nenghai Yu [ Paper ] [ Code ]

[2024_053] Point Could Mamba: Point Cloud Learning via State Space Model , Tao Zhang, Xiangtai Li, Haobo Yuan, Shunping Ji, Shuicheng Yan [ Paper ] [ Code ]

[2024_052] Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning , Chi-Sheng Chen, Guan-Ying Chen, Dong Zhou, Di Jiang, Dai-Shi Chen [ Paper ] [ Code ]

[2024_051] MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation , Jiahao Huang, Liutao Yang, Fanwen Wang, Yinzhe Wu, Yang Nan, Angelica I. Aviles-Rivero, Carola-Bibiane Schönlieb, Daoqiang Zhang, Guang Yang [ Paper ] [ Code ]

[2024_050] MambaIR: A Simple Baseline for Image Restoration with State-Space Model , Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, Shu-Tao Xia [ Paper ] [ Code ]

[2024_049] State Space Models for Event Cameras , Nikola Zubić, Mathias Gehrig, Davide Scaramuzza [ Paper ]

[2024_048][ICLR 2024] FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores , Daniel Y Fu, Hermann Kumbong, Eric Nguyen, Christopher Re [ Paper ]

[2024_047] Variational quantization for state space models , Etienne David, Jean Bellot, Sylvain Le Corff [ Paper ]

[2024_046] Efficient Long Sequence Modeling via State Space Augmented Transformer , Simiao Zuo, Xiaodong Liu, Jian Jiao, Denis X Charles, Eren Manavoglu, Tuo Zhao, Jianfeng Gao [ Paper ]

[2024_045][ICLR 2024] Robustifying State-space Models for Long Sequences via Approximate Diagonalization , Annan Yu, Arnur Nigmetov, Dmitriy Morozov, Michael W. Mahoney, N. Benjamin Erichson [ Paper ]

[2024_044] From generalization analysis to optimization designs for state space models , Fusheng Liu, Qianxiao Li [ Paper ]

[2024_043] A 2-Dimensional State Space Layer for Spatial Inductive Bias , Ethan Baron, Itamar Zimerman, Lior Wolf [ Paper ]

[2024_042][ICLR 2024] Hieros: Hierarchical Imagination on Structured State Space Sequence World Models , Paul Mattes, Rainer Schlosser, Ralf Herbrich [ Paper ]

[2024_041] S4++: Elevating Long Sequence Modeling with State Memory Reply , [ Paper ]

[2024_040][Rejected by ICLR 2024] Mamba: Linear-Time Sequence Modeling with Selective State Spaces , Albert Gu, Tri Dao [ Paper ] [ Mamba: The Hard Way ] [ annotated-mamba ]

[2024_039][ICLR 2024] Gated recurrent neural networks discover attention , Nicolas Zucchet, Seijin Kobayashi, Yassir Akram, Johannes Von Oswald, Maxime Larcher, Angelika Steger, Joao Sacramento [ Paper ]

[2024_038][ICLR 2024] GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling , Tobias Katsch [ Paper ]

[2024_037][ICLR 2024] Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors , Ido Amos, Jonathan Berant, Ankit Gupta [ Paper ]

[2024_036] [ICLR 2024] Mastering Memory Tasks with World Models , Mohammad Reza Samsami, Artem Zholus, Janarthanan Rajendran, Sarath Chandar [ Paper ]

[2024_035] Spectral State Space Models , Naman Agarwal, Daniel Suo, Xinyi Chen, Elad Hazan [ Paper ]

[2024_034] Graph Mamba: Towards Learning on Graphs with State Space Models , Ali Behrouz, Farnoosh Hashemi [ Paper ]

[2024_033] Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks , Jongho Park, Jaeseung Park, Zheyang Xiong, Nayoung Lee, Jaewoong Cho, Samet Oymak, Kangwook Lee, Dimitris Papailiopoulos [ Paper ]

[2024_032] Is Mamba Capable of In-Context Learning? Riccardo Grazzi, Julien Siems, Simon Schrodi, Thomas Brox, Frank Hutter [ Paper ]

[2024_031] LOCOST: State-Space Models for Long Document Abstractive Summarization , Florian Le Bronnec, Song Duong, Mathieu Ravaut, Alexandre Allauzen, Nancy F. Chen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari [ Paper ] [ Code ]

[2024_030] RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks , Haowen Hou, F. Richard Yu [ Paper ] [ Code ]

[2024_029] BlackMamba: Mixture of Experts for State-Space Models , Quentin Anthony, Yury Tokpanov, Paolo Glorioso, Beren Millidge [ Paper ] [ Code ]

[2024_028] Recurrent Distance Filtering for Graph Representation Learning , Yuhui Ding, Antonio Orvieto, Bobby He, Thomas Hofmann [ Paper ] [ Code ]

[2024_027] SSM Meets Video Diffusion Models: Efficient Video Generation with Structured State Spaces , Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo [ Paper ]

[2024_026] Pan-Mamba: Effective pan-sharpening with State Space Model , Xuanhua He, Ke Cao, Keyu Yan, Rui Li, Chengjun Xie, Jie Zhang, Man Zhou [ Paper ] [ Code ]

[2024_025] Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation , Ziyang Wang, Chao Ma [ Paper ] [ Code ]

[2024_024] PointMamba: A Simple State Space Model for Point Cloud Analysis , Dingkang Liang, Xin Zhou, Xinyu Wang, Xingkui Zhu, Wei Xu, Zhikang Zou, Xiaoqing Ye, Xiang Bai [ Paper ] [ Code ]

[2024_023] P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular Segmentation , Zi Ye, Tianxiang Chen [ Paper ]

[2024_022] Semi-Mamba-UNet: Pixel-Level Contrastive Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation , Ziyang Wang, Chao Ma [ Paper ]

[2024_021] FD-Vision Mamba for Endoscopic Exposure Correction , Zhuoran Zheng, Jun Zhang, [ Paper ]

[2024_020] Scalable Diffusion Models with State Space Backbone , Zhengcong Fei, Mingyuan Fan, Changqian Yu, Junshi Huang [ Paper ] [ Code ]

[2024_019] Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data , Shufan Li, Harkanwar Singh, Aditya Grover [ Paper ]

[2024_018] Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation , Ziyang Wang, Jian-Qing Zheng, Yichi Zhang, Ge Cui, Lei Li [ Paper ] [ Code ]

[2024_017] MambaTab: A Simple Yet Effective Approach for Handling Tabular Data , Md Atik Ahamed1, Qiang Cheng [ Paper ]

[2024_016] nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model , Haifan Gong, Luoyao Kang, Yitao Wang, Xiang Wan, Haofeng Li [ Paper ] [ Code ]

[2024_015] U-shaped Vision Mamba for Single Image Dehazing , Zhuoran Zheng, Chen Wu [ Paper ]

[2024_014] Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces , Chloe Wang, Oleksii Tsepa, Jun Ma, Bo Wang [ Paper ] [ Code ]

[2024_013] VM-UNet: Vision Mamba UNet for Medical Image Segmentation , Jiacheng Ruan, Suncheng Xiang [ Paper ] [ Code ]

[2024_012] Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining , Jiarun Liu, Hao Yang, Hong-Yu Zhou, Yan Xi, Lequan Yu, Yizhou Yu, Yong Liang, Guangming Shi, Shaoting Zhang, Hairong Zheng, Shanshan Wang [ Paper ] [ Code ]

[2024_011] Ma, Jun, Feifei Li, and Bo Wang. " U-mamba: Enhancing long-range dependency for biomedical image segmentation ." arXiv preprint arXiv:2401.04722 (2024). [ Paper ] [ Code ]

[2024_010] Vivim: a Video Vision Mamba for Medical Video Object Segmentation , Yijun Yang, Zhaohu Xing, and Lei Zhu [ Paper ] [ Code ]

[2024_009] Wang, Junxiong, et al. " MambaByte: Token-free Selective State Space Model. " arXiv preprint arXiv:2401.13660 (2024). [ Paper ] [ Code ]

[2024_008] MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts. Pióro, M., Ciebiera, K., Król, K., Ludziejewski, J., & Jaszczur, S. (2024). arXiv preprint arXiv:2401.04081. [ Paper ]

[2024_007] [ICLR-2024] MASTERING MEMORY TASKS WITH WORLD MODELS [ Paper ]

[2024_006] MambaMorph: a Mamba-based Backbone with Contrastive Feature Learning for Deformable MR-CT Registration , Tao Guo, Yinuo Wang, and Cai Meng [ Paper ] [ Code ]

[2024_005] SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation , [ Paper ] [ Code ]

[2024_003] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model , Lianghui Zhu1∗, Bencheng Liao1∗, Qian Zhang2, Xinlong Wang3, Wenyu Liu1, Xinggang Wang [ Paper ] [ Code ]

[2024_002] VMamba: Visual State Space Model , Yue Liu1,Yunjie Tian1,Yuzhong Zhao1, Hongtian Yu1, Lingxi Xie2, Yaowei Wang3, Qixiang Ye1, Yunfan Liu1 [ Paper ] [ Code ]

[2024_001] Theoretical Foundations of Deep Selective State-Space Models , Nicola Muca Cirone, Antonio Orvieto, Benjamin Walker, Cristopher Salvi, Terry Lyons [ Paper ]

[2023_018] [CHIL 2023] Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models , Siyi Tang, Jared A. Dunnmon, Liangqiong Qu, Khaled K. Saab, Tina Baykaner, Christopher Lee-Messer, Daniel L. Rubin [ Paper ]

[2023_017] "StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization." Wang, Shida, and Qianxiao Li. arXiv preprint arXiv:2311.14495 (2023). [ Paper ] [ Code ]

[2023_016] State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory , Shida Wang, Beichen Xue [ Paper ]

[2023_015] Spiking Structured State Space Model for Monaural Speech Enhancement . Du, Y., Liu, X., & Chua, Y. (2023). arXiv preprint arXiv:2309.03641. [ Paper ]

[2023_014] Mastering Diverse Domains through World Models , Danijar Hafner,12 Jurgis Pasukonis,1 Jimmy Ba,2 Timothy Lillicrap [ Paper ] [ Code ]

[2023_013] Selective Structured State-Spaces for Long-Form Video Understanding , Jue Wang Wentao Zhu Pichao Wang Xiang Yu Linda Liu Mohamed Omar Raffay Hamid [ Paper ]

[2023_012] Mamba: Linear-Time Sequence Modeling with Selective State Spaces , Albert Gu*1and Tri Dao [ Paper ] [ Github ]

[2023_011] [NeurIPS 2023] Structured State Space Models for In-Context Reinforcement Learning , Chris Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Foerster, Satinder Singh, Feryal Behbahani [ Paper ] [ Code ]

[2023_010] Diffusion Models Without Attention , Jing Nathan Yan, Jiatao Gu, Alexander M. Rush [ Paper ]

[2023_009] Hierarchically Gated Recurrent Neural Network for Sequence Modeling , Zhen Qin, Songlin Yang, Yiran Zhong [ Paper ] [ Code ]

[2023_008] Retentive Network: A Successor to Transformer for Large Language Models , Yutao Sun, Li Dong, Shaohan Huang, Shuming Ma, Yuqing Xia, Jilong Xue, Jianyong Wang, Furu Wei [ Paper ] [ Code ]

[2023_007] Convolutional State Space Models for Long-Range Spatiotemporal Modeling , Jimmy T.H. Smith, Shalini De Mello, Jan Kautz, Scott W. Linderman, Wonmin Byeon [ Paper ] [ Code ]

[2023_006] Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions , Stefano Massaroli, Michael Poli, Daniel Y. Fu, Hermann Kumbong, Rom N. Parnichkun, Aman Timalsina, David W. Romero, Quinn McIntyre, Beidi Chen, Atri Rudra, Ce Zhang, Christopher Re, Stefano Ermon, Yoshua Bengio [ Paper ]

[2023_005] Structured state-space models are deep Wiener models , Fabio Bonassi, Carl Andersson, Per Mattsson, Thomas B. Schön [ Paper ]

[2023_004] Zoology: Measuring and Improving Recall in Efficient Language Models , Simran Arora, Sabri Eyuboglu, Aman Timalsina, Isys Johnson, Michael Poli, James Zou, Atri Rudra, Christopher Ré [ Paper ]

[2023_003] [ICML 2023] Resurrecting Recurrent Neural Networks for Long Sequences , Antonio Orvieto · Samuel Smith · Albert Gu · Anushan Fernando · Caglar Gulcehre · Razvan Pascanu · Soham De [ Paper ]

[2023_002] Hyena Hierarchy: Towards Larger Convolutional Language Models , Michael Poli, Stefano Massaroli, Eric Nguyen, Daniel Y. Fu, Tri Dao, Stephen Baccus, Yoshua Bengio, Stefano Ermon, Christopher Ré [ Paper ]

[2023_001] [ICLR 2023] Simplified State Space Layers for Sequence Modeling , Jimmy T.H. Smith, Andrew Warrington, Scott Linderman [ Paper ]

[2022_009] [ECCV-2022] Long Movie Clip Classification with State-Space Video Models , Md Mohaiminul Islam, Gedas Bertasius [ Paper ] [ Code ]

[2022_008] [NIPS-2022] "S4nd: Modeling images and videos as multidimensional signals with state spaces." Nguyen, Eric, et al. Advances in neural information processing systems 35 (2022): 2846-2861. [ Paper ] [ Code ]

[2022_007] [Pre-training] Wang, J., Yan, J. N., Gu, A., & Rush, A. M. (2022). Pretraining without attention . arXiv preprint arXiv:2212.10544. [ Paper ] [ Code ]

[2022_006] Long Range Language Modeling via Gated State Spaces , Harsh Mehta1∗ Ankit Gupta2 Ashok Cutkosky3 Behnam Neyshabur1 [ Paper ]

[2022_005] [ICML2022] It’s Raw! Audio Generation with State-Space Models , Karan Goel, Albert Gu, Chris Donahue, and Christopher R´e [ Paper ]

[2022_004] Diagonal State Spaces are as Effective as Structured State Spaces , Ankit Gupta˚Albert Gu Jonathan Berant [ Paper ]

[2022_003] How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections , Albert Gu∗†, Isys Johnson∗‡, Aman Timalsina‡, Atri Rudra‡, and Christopher R´e† [ Paper ]

[2022_002] On the Parameterization and Initialization of Diagonal State Space Models , Albert Gu†, Ankit Gupta‡, Karan Goel†, and Christopher R´e† [ Paper ]

[2022_001] Efficiently Modeling Long Sequences with Structured State Spaces , Albert Gu, Karan Goel, Christopher Ré [ Paper ] [ The Annotated S4 ]

Year 2021 and Before

[2021_003] Efficiently Modeling Long Sequences with Structured State Spaces , Albert Gu, Karan Goel, and Christopher R´e [ Paper ] [ Code ]

[2021_002] HiPPO: Recurrent Memory with Optimal Polynomial Projections , Albert Gu∗†, Tri Dao∗†, Stefano Ermon†, Atri Rudra‡, and Christopher Ré† [ Paper ] [ Code ]

[2021_001] Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers , Albert Gu†, Isys Johnson†, Karan Goel†, Khaled Saab†, Tri Dao†, Atri Rudra‡, and Christopher Ré† [ Paper ]

Related Models

Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models , Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Junshi Huang [ Paper ]

"Retentive network: A successor to transformer for large language models." Sun, Yutao, et al. arXiv preprint arXiv:2307.08621 (2023). [ Paper ] [ Code ]

TLS-RWKV: Real-Time Online Action Detection with Temporal Label Smoothing . Zhu, Z., Shao, W. & Jiao, D. Neural Process Lett 56, 57 (2024). [ Paper ]

RRWKV: Capturing Long-range Dependencies in RWKV , Leilei Wang [ Paper ]

RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks , Haowen Hou, F. Richard Yu [ Paper ] [ Code ]

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures , Yuchen Duan, Weiyun Wang, Zhe Chen, Xizhou Zhu, Lewei Lu, Tong Lu, Yu Qiao, Hongsheng Li, Jifeng Dai, Wenhai Wang [ Paper ] [ Code ]

RWKV: Reinventing RNNs for the Transformer Era , Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Matteo Grella, Kranthi Kiran GV, Xuzheng He, Haowen Hou, Jiaju Lin, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartlomiej Koptyra, Hayden Lau, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Bolun Wang, Johan S. Wind, Stanislaw Wozniak, Ruichong Zhang, Zhenyuan Zhang, Qihang Zhao, Peng Zhou, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu [ Paper ]

Other Useful URLs

• [ awesome-ssm-ml ]
• [ Awesome-Mamba-Papers ]
• [ XiudingCai/Awesome-Mamba-Collection ]
• [ Awesome-state-space-models ] Collection of papers/repos on state-space models.
• [ mamba-minimal ] Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
• [ mamba.py ] A simple and efficient Mamba implementation in PyTorch and MLX.
• [ Introduction to State Space Models (SSM) ]
• [ State-Space Modelling by Kevin Kotzé ]
• [ Structured State Spaces: Combining Continuous-Time, Recurrent, and Convolutional Models ]
• [ A Visual Guide to Mamba and State Space Models ---An Alternative to Transformers for Language Modeling ] FEB 19, 2024, by MAARTEN GROOTENDORST.
• [ Structured State Spaces: A Brief Survey of Related Models ] by Albert Gu, Karan Goel, Khaled Saab, and Chris Ré

If you think this survey is helpful, please feel free to leave a star ⭐️ and cite our paper:

Star History

Contributors 5

Paper: To understand cognition—and its dysfunction—neuroscientists must learn its rhythms

Thought emerges and is controlled in the brain via the rhythmically and spatially coordinated activity of millions of neurons, scientists argue in a new article. Understanding cognition and its disorders requires studying it at that level.

It could be very informative to observe the pixels on your phone under a microscope, but not if your goal is to understand what a whole video on the screen shows. Cognition is much the same kind of emergent property in the brain . It can only be understood by observing how millions of cells act in coordination, argues a trio of MIT neuroscientists. In a new article , they lay out a framework for understanding how thought arises from the coordination of neural activity driven by oscillating electric fields—also known as brain “waves” or “rhythms.”

Historically dismissed solely as byproducts of neural activity, brain rhythms are actually critical for organizing it, write Picower Professor Earl Miller and research scientists Scott Brincat and Jefferson Roy in Current Opinion in Behavioral Science . And while neuroscientists have gained tremendous knowledge from studying how individual brain cells connect and how and when they emit “spikes” to send impulses through specific circuits, there is also a need to appreciate and apply new concepts at the brain rhythm scale, which can span individual, or even multiple, brain regions.

“Spiking and anatomy are important but there is more going on in the brain above and beyond that,” said senior author Miller, a faculty member in The Picower Institute for Learning and Memory and the Department of Brain and Cognitive Sciences at MIT. “There’s a whole lot of functionality taking place at a higher level, especially cognition.”

The stakes of studying the brain at that scale, the authors write, might not only include understanding healthy higher-level function but also how those functions become disrupted in disease.

“Many neurological and psychiatric disorders, such as schizophrenia, epilepsy and Parkinson’s involve disruption of emergent properties like neural synchrony,” they write. “We anticipate that understanding how to interpret and interface with these emergent properties will be critical for developing effective treatments as well as understanding cognition.”

The emergence of thoughts

The bridge between the scale of individual neurons and the broader-scale coordination of many cells is founded on electric fields, the researchers write. Via a phenomenon called “ephaptic coupling,” the electrical field generated by the activity of a neuron can influence the voltage of neighboring neurons, creating an alignment among them. In this way, electric fields both reflect neural activity but also influence it. In a paper in 2022 , Miller and colleagues showed via experiments and computational modeling that the information encoded in the electric fields generated by ensembles of neurons can be read out more reliably than the information encoded by the spikes of individual cells. In 2023 Miller’s lab provided evidence that rhythmic electrical fields may coordinate memories between regions.

At this larger scale, in which rhythmic electric fields carry information between brain regions, Miller’s lab has published numerous studies showing that lower-frequency rhythms in the so-called “beta” band originate in deeper layers of the brain’s cortex and appear to regulate the power of faster-frequency “gamma” rhythms in more superficial layers. By recording neural activity in the brains of animals engaged in working memory games the lab has shown that beta rhythms carry “top down” signals to control when and where gamma rhythms can encode sensory information, such as the images that the animals need to remember in the game.

Some of the lab’s latest evidence suggests that beta rhythms apply this control of cognitive processes to physical patches of the cortex, essentially acting like stencils that pattern where and when gamma can encode sensory information into memory, or retrieve it. According to this theory, which Miller calls “ Spatial Computing ,” beta can thereby establish the general rules of a task (for instance, the back and forth turns required to open a combination lock), even as the specific information content may change (for instance, new numbers when the combination changes). More generally, this structure also enables neurons to flexibly encode more than one kind of information at a time, the authors write, a widely observed neural property called “mixed selectivity.” For instance, a neuron encoding a number of the lock combination can also be assigned, based on which beta-stenciled patch it is in, the particular step of the unlocking process that the number matters for.

In the new study Miller, Brincat and Roy suggest another advantage consistent with cognitive control being based on an interplay of large-scale coordinated rhythmic activity: “Subspace coding.” This idea postulates that brain rhythms organize the otherwise massive number of possible outcomes that could result from, say, 1,000 neurons engaging in independent spiking activity. Instead of all the many combinatorial possibilities, many fewer “subspaces” of activity actually arise, because neurons are coordinated, rather than independent. It is as if the spiking of neurons is like a flock of birds coordinating their movements.  Different phases and frequencies of brain rhythms provide this coordination, aligned to amplify each other, or offset to prevent interference. For instance, if a piece of sensory information needs to be remembered, neural activity representing it can be protected from interference when new sensory information is perceived.

“Thus the organization of neural responses into subspaces can both segregate and integrate information,” the authors write.

The power of brain rhythms to coordinate and organize information processing in the brain is what enables functional cognition to emerge at that scale, the authors write. Understanding cognition in the brain, therefore, requires studying rhythms.

“Studying individual neural components in isolation—individual neurons and synapses—has made enormous contributions to our understanding of the brain and remains important,” the authors conclude. “However, it’s becoming increasingly clear that, to fully capture the brain’s complexity, those components must be analyzed in concert to identify, study, and relate their emergent properties.”

Related Articles

Study reveals a universal pattern of brain wave frequencies.

Anesthesia blocks sensation by cutting off communication within the cortex

Anesthesia technology precisely controls unconsciousness in animal tests

A multifunctional tool for cognitive neuroscience

AI Index Report

Welcome to the seventh edition of the AI Index report. The 2024 Index is our most comprehensive to date and arrives at an important moment when AI’s influence on society has never been more pronounced. This year, we have broadened our scope to more extensively cover essential trends such as technical advancements in AI, public perceptions of the technology, and the geopolitical dynamics surrounding its development. Featuring more original data than ever before, this edition introduces new estimates on AI training costs, detailed analyses of the responsible AI landscape, and an entirely new chapter dedicated to AI’s impact on science and medicine.

Read the 2024 AI Index Report

The AI Index report tracks, collates, distills, and visualizes data related to artificial intelligence (AI). Our mission is to provide unbiased, rigorously vetted, broadly sourced data in order for policymakers, researchers, executives, journalists, and the general public to develop a more thorough and nuanced understanding of the complex field of AI.

The AI Index is recognized globally as one of the most credible and authoritative sources for data and insights on artificial intelligence. Previous editions have been cited in major newspapers, including the The New York Times, Bloomberg, and The Guardian, have amassed hundreds of academic citations, and been referenced by high-level policymakers in the United States, the United Kingdom, and the European Union, among other places. This year’s edition surpasses all previous ones in size, scale, and scope, reflecting the growing significance that AI is coming to hold in all of our lives.

Steering Committee Co-Directors

Ray Perrault

Steering committee members.

Erik Brynjolfsson

John Etchemendy

Katrina Ligett

Terah Lyons

James Manyika

Juan Carlos Niebles

Vanessa Parli

Yoav Shoham

Russell Wald

Staff members.

Loredana Fattorini

Nestor Maslej

Letter from the co-directors.

A decade ago, the best AI systems in the world were unable to classify objects in images at a human level. AI struggled with language comprehension and could not solve math problems. Today, AI systems routinely exceed human performance on standard benchmarks.

Progress accelerated in 2023. New state-of-the-art systems like GPT-4, Gemini, and Claude 3 are impressively multimodal: They can generate fluent text in dozens of languages, process audio, and even explain memes. As AI has improved, it has increasingly forced its way into our lives. Companies are racing to build AI-based products, and AI is increasingly being used by the general public. But current AI technology still has significant problems. It cannot reliably deal with facts, perform complex reasoning, or explain its conclusions.

AI faces two interrelated futures. First, technology continues to improve and is increasingly used, having major consequences for productivity and employment. It can be put to both good and bad uses. In the second future, the adoption of AI is constrained by the limitations of the technology. Regardless of which future unfolds, governments are increasingly concerned. They are stepping in to encourage the upside, such as funding university R&D and incentivizing private investment. Governments are also aiming to manage the potential downsides, such as impacts on employment, privacy concerns, misinformation, and intellectual property rights.

As AI rapidly evolves, the AI Index aims to help the AI community, policymakers, business leaders, journalists, and the general public navigate this complex landscape. It provides ongoing, objective snapshots tracking several key areas: technical progress in AI capabilities, the community and investments driving AI development and deployment, public opinion on current and potential future impacts, and policy measures taken to stimulate AI innovation while managing its risks and challenges. By comprehensively monitoring the AI ecosystem, the Index serves as an important resource for understanding this transformative technological force.

On the technical front, this year’s AI Index reports that the number of new large language models released worldwide in 2023 doubled over the previous year. Two-thirds were open-source, but the highest-performing models came from industry players with closed systems. Gemini Ultra became the first LLM to reach human-level performance on the Massive Multitask Language Understanding (MMLU) benchmark; performance on the benchmark has improved by 15 percentage points since last year. Additionally, GPT-4 achieved an impressive 0.97 mean win rate score on the comprehensive Holistic Evaluation of Language Models (HELM) benchmark, which includes MMLU among other evaluations.

Although global private investment in AI decreased for the second consecutive year, investment in generative AI skyrocketed. More Fortune 500 earnings calls mentioned AI than ever before, and new studies show that AI tangibly boosts worker productivity. On the policymaking front, global mentions of AI in legislative proceedings have never been higher. U.S. regulators passed more AI-related regulations in 2023 than ever before. Still, many expressed concerns about AI’s ability to generate deepfakes and impact elections. The public became more aware of AI, and studies suggest that they responded with nervousness.

Ray Perrault Co-director, AI Index

Our Supporting Partners

Analytics & Research Partners

Stay up to date on the AI Index by subscribing to the  Stanford HAI newsletter.