ICLR 2024

Awards Committee: Eunsol Choi, Katja Hofmann, Ming-Yu Liu, Nan Jiang, Stephan Günnemann, Suvrit Sra, Thomas Kipf, Volkan Cevher

(This post is written by the Awards Committee, lightly edited by the Program Chairs.)

Selection Process

The ICLR 2024 Outstanding Paper Committee went through the following selection process to identify a collection of outstanding papers and honorable mentions that showcase excellent research presented at this conference. 

The committee began with an initial pool of 44 papers provided by the program chairs. During phase 1, each member of the committee ranked these papers based on how comfortable they would be reviewing the papers based on their expertise, while avoiding conflicts of interest. Then, each paper was assigned two committee members, and each in turn received about a dozen papers to review. Then, each member was encouraged to submit up to three nominations in their batch through an anonymous form. This process generated ~20 shortlisted papers. During Phase 2, all members of the committee familiarized themselves with those papers. The second reviewer (who did not submit a nomination for the paper) was also encouraged to share their thoughts. During the final phase, the committee discussed the nominated papers together and decided on outstanding paper / honorable mentions. The committee also aimed to highlight a wide range of research contributions, from theoretical insights, practical impacts, exceptional writing, and experimental rigor. Throughout the process, the committee reached out to external experts when appropriate and would like to thank all those who contributed to this process.

In total there are 5 Outstanding Paper winners, and 11 Honorable Mentions.  Congratulations to all the authors for their exceptional contributions to ICLR!

Award Winners

Generalization in diffusion models arises from geometry-adaptive harmonic representations
Zahra Kadkhodaie, Florentin Guth, Eero P Simoncelli, Stéphane Mallat
https://openreview.net/forum?id=ANvmVS2Yr0
https://iclr.cc/virtual/2024/oral/19783

This paper provides an important in-depth analysis on generalization and memorization aspects of image diffusion models. The authors empirically study when an image generative model switches from memorizing the input to a generalization regime and they further provide an explanation of this phenomenon in terms of architectural inductive biases by making a connection to ideas from harmonic analysis via “geometry-adaptive harmonic representations”. The paper covers a critical missing piece of our understanding of visual generative models and will likely inspire future important theory work in this area.

Learning Interactive Real-World Simulators
Sherry Yang, Yilun Du, Seyed Kamyar Seyed Ghasemipour, Jonathan Tompson, Leslie Pack Kaelbling, Dale Schuurmans, Pieter Abbeel
https://openreview.net/forum?id=sFyTZEqmUY
https://iclr.cc/virtual/2024/oral/19722

Aggregating data across multiple sources to train foundation models for robotics is a long-term ambitious goal. It poses significant challenges due to different robots having different sensory-motor interfaces which hinder training across large-scale datasets. This work, UniSim, is a significant step in this direction and an engineering feat, aggregating data using a unified interface based on visual perceptions and text descriptions of controls, and training a robotics simulator from the data by leveraging latest developments in vision and language domains. 

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
Ido Amos, Jonathan Berant, Ankit Gupta
https://openreview.net/forum?id=PdaPky8MUn
https://iclr.cc/virtual/2024/oral/19761

This paper dives deep into understanding the ability of recently proposed state-space models and transformer architectures to model long-term sequential dependencies. Surprisingly, the authors find that training transformer models from scratch leads to an under-estimation of their performance and demonstrates dramatic gains can be achieved with a pre-training and fine-tuning setup. The paper is exceptionally well executed and exemplary in its focus on simplicity and systematic insights.

Protein Discovery with Discrete Walk-Jump Sampling
Nathan C. Frey, Dan Berenberg, Karina Zadorozhny, Joseph Kleinhenz, Julien Lafrance-Vanasse, Isidro Hotzel, Yan Wu, Stephen Ra, Richard Bonneau, Kyunghyun Cho, Andreas Loukas, Vladimir Gligorijevic, Saeed Saremi
https://openreview.net/forum?id=zMPHKOmQNb
https://iclr.cc/virtual/2024/oral/19713

This paper addresses the problem of sequence-based antibody design, a timely and important application for generative models of protein sequences. To this end, the authors introduce an innovative and effective new modeling approach specifically tailored to the problem of handling discrete protein sequence data. In addition to validating the method in silico, the authors perform extensive wet lab experiments to measure antibody binding affinity in vitro, demonstrating the effectiveness of their generative method.

Vision Transformers Need Registers
Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski
https://openreview.net/forum?id=2dnO3LLiJ1
https://iclr.cc/virtual/2024/oral/19794

This paper identifies artifacts in feature maps of vision transformer networks, characterized by high-norm tokens in low-informative background areas. The authors provide key hypotheses for why this is happening and provide a simple yet elegant solution to address these artifacts using additional register tokens, enhancing model performance on various tasks. The insights gained from this work can also impact other application areas. The paper is very well-written and provides a great example of conducting research – identifying an issue, understanding why it is happening, and then providing a solution. 

Honorable mentions

Amortizing intractable inference in large language models
Edward J Hu, Moksh Jain, Eric Elmoznino, Younesse Kaddar, Guillaume Lajoie, Yoshua Bengio, Nikolay Malkin
https://openreview.net/forum?id=Ouj6p4ca60
https://iclr.cc/virtual/2024/oral/19763

The paper proposes a promising alternative to autoregressive decoding in LLMs from a Bayesian inference perspective that can inspire follow-up studies. 

Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization
Ian Gemp, Luke Marris, Georgios Piliouras
https://openreview.net/forum?id=cc8h3I3V4E
https://iclr.cc/virtual/2024/oral/19744

An exceptionally clearly written paper, making progress on the important problem of developing efficient and scalable Nash solvers.

Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
Bohang Zhang, Jingchu Gai, Yiheng Du, Qiwei Ye, Di He, Liwei Wang
https://openreview.net/forum?id=HSKaGOi7Ar
https://iclr.cc/virtual/2024/oral/19773

Expressivity of GNNs is an important topic for which current solutions, such as the Weisfeiler-Lehman test, still come with significant limitations. The authors propose a new “expressivity theory” based on homomorphism counts.

Flow Matching on General Geometries
Ricky T. Q. Chen, Yaron Lipman
https://openreview.net/forum?id=g7ohDlTITL
https://iclr.cc/virtual/2024/oral/19740

This paper tackles the challenging yet important problem of generative modeling on general geometric manifolds, for which it proposes a practical and efficient algorithm. The paper is presented exceptionally well and features a comprehensive experimental validation on a wide range of tasks.

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
Shashanka Venkataramanan, Mamshad Nayeem Rizve, Joao Carreira, Yuki M Asano, Yannis Avrithis
https://openreview.net/forum?id=Yen1lGns2o
https://iclr.cc/virtual/2024/oral/19752

The paper proposes a novel path to self-supervised image pre-training, by learning from continuous videos. The paper contributes both new types of data and a method to learn from novel data.  

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
Yichen Wu, Long-Kai Huang, Renzhen Wang, Deyu Meng, Ying Wei
https://openreview.net/forum?id=TpD2aG1h0D
https://iclr.cc/virtual/2024/oral/19759

The authors propose a new variance reduction approach to meta continuous learning. The approach is presented well and has not only practical impact but is also backed up with regret analysis.

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Suyu Ge, Yunan Zhang, Liyuan Liu, Minjia Zhang, Jiawei Han, Jianfeng Gao
https://openreview.net/forum?id=uNrFpDPMyo
https://iclr.cc/virtual/2024/oral/19718

The paper targets the critical KV cache compression problem with great impact on transformer based LLMs, reducing the memory with a simple idea that can be deployed without resource intensive fine-tuning or re-training. The approach is quite simple and yet is shown to be quite effective.

Proving Test Set Contamination in Black-Box Language Models
Yonatan Oren, Nicole Meister, Niladri S. Chatterji, Faisal Ladhak, Tatsunori Hashimoto
https://openreview.net/forum?id=KS8mIvetg2
https://iclr.cc/virtual/2024/oral/19769

A simple yet elegant method to test whether a supervised-learning dataset has been included in LLM training.

Robust agents learn causal world models
Jonathan Richens, Tom Everitt
https://openreview.net/forum?id=pOoKI3ouv1
https://iclr.cc/virtual/2024/oral/19724

This paper makes progress on laying theoretical foundations towards understanding the role of causal reasoning in agents’ ability to generalize to new domains and has potential implications for a range of related fields.

The mechanistic basis of data dependence and abrupt learning in an in-context classification task
Gautam Reddy
https://openreview.net/forum?id=aN4Jf6Cx69
https://iclr.cc/virtual/2024/oral/19749

A timely and exceptionally systematic study of the mechanics that underlie in-context vs. in-weight learning at a point where we are only starting to understand these phenomena. 

Towards a statistical theory of data selection under weak supervision
Germain Kolossov, Andrea Montanari, Pulkit Tandon
https://openreview.net/forum?id=HhfcNgQn6p
https://iclr.cc/virtual/2024/oral/19772

The paper establishes statistical foundations for data subset selection and identifies the shortcomings of popular data selection methods.

As machine learning conferences grow, we as a community need to put more thought and planning into maintaining a fair review process. During the recent round of reviews, several issues pertaining to academic integrity came to our attention.  This prompted us to conduct an investigation, including, e.g., partnering with sister conferences for checking for dual submissions. 

We emphasize that ICLR received over 7000 submissions, and these issues represent only a handful of cases. Most reviewers worked tirelessly to maintain the high standards of our review systems – we would like to thank you all for your efforts. 

Nonetheless, our investigation (much of which was via automated scripts) found multiple cases of plagiarism, dual submissions, and evidence of collusion by groups of reviewers and authors.  These behaviors are all in direct violation of the Code of Ethics, and we have reason to believe that they are happening across many top AI conferences.  

Our current activities include:

• Establishing a committee dedicated to reviewing detected cases and recommending penalties (if appropriate).
• Coordinating with other AI/ML conferences to conduct cross-conference investigations to address these issues.

Note that ICLR uses OpenReview which automatically detects conflict of interests as long as they are added to your profile. Keeping your profile up-to-date is a great way to avoid the possible appearance of a conflict of interest. 

We encourage anyone with additional information to email iclr2024.programchairs@gmail.com or submit via this form (anonymity enabled).  We are interested in evidence of:

• Plagiarism
• Dual submissions
• Collusion

All communications will be treated with the highest confidentiality possible, and identities of anyone coming forward will be protected.

Hugging Face is hosting a demo site for authors to find and claim their papers on the Hugging Face website and discuss those papers on dedicated pages:
https://huggingface.co/spaces/ICLR2024/ICLR2024-papers
The page includes all accepted papers, along with linked datasets, models, and demos.

If you have any questions, please contact the Hugging Face team via ahsen@huggingface.co

We are pleased to announce the Invited Speakers for ICLR 2024.  These speakers were selected to cover a range of topics, both within core machine learning, and also in adjacent areas of interest (e.g., legal considerations, sustainability, and drug design).  Those attending ICLR can see the full schedule here (if attending in person, please set your timezone to Europe/Vienna).

Invited Speakers in alphabetical order (talk titles & abstracts subject to change):

Kyunghyun Cho, NYU & Genentech (Prescient Design)

Talk Title: “Machine Learning in Prescient Design’s Lab-in-the-Loop Antibody Design”

Abstract: TBA

Priya Donti, MIT & Climate Change AI

Talk Title: “ Optimization-in-the-loop ML for climate and energy”

Abstract: TBA

Kate Downing, Law Offices of Kate Downing

Talk Title: “Legal Fundamentals for AI Researchers”

Abstract: This talk will cover fundamental legal principles all AI researchers should understand. This talk will explore why legislators are looking at new laws specifically for AI and the goals they want to accomplish with those laws. It will also cover legal risks related to using training datasets, understanding dataset licenses, and options for licensing models in an open fashion.

Raia Hadsell, Google DeepMind

Talk Title: “Learning through AI’s winters and springs: unexpected truths on the road to AGI”

Abstract: After decades of steady progress and occasional setbacks, the field of AI now finds itself at an inflection point. AI products have exploded into the mainstream, we’ve yet to hit the ceiling of scaling dividends, and the community is asking itself what comes next. In this talk, Raia will draw on her 20 years experience as an AI researcher and AI leader to examine how our assumptions about the path to Artificial General Intelligence (AGI) have evolved over time, and to explore the unexpected truths that have emerged along the way. From reinforcement learning to distributed architectures and the potential of neural networks to revolutionize scientific domains, Raia argues that embracing lessons from the past offers valuable insights for AI’s future research roadmap.

Moritz Hardt, Max Planck Institute for Intelligent Systems, Tübingen

Talk Title: “The emerging science of benchmarks”

Abstract: Benchmarks are the keystone that hold the machine learning community together. Growing as a research paradigm since the 1980s, there’s much we’ve done with them, but little we know about them.  In this talk, I will trace the rudiments of an emerging science of benchmarks through selected empirical and theoretical observations. Specifically, we’ll discuss the role of annotator errors, external validity of model rankings, and the promise of multi-task benchmarks. The results in each case challenge conventional wisdom and underscore the benefits of developing a science of benchmarks.

Devi Parikh, Georgia Tech

Talk Title: “Stories from my life“

Abstract: This is going to be an unusual AI conference keynote talk. When we talk about why the technological landscape is the way it is, we talk a lot about the macro shifts – the internet, the data, the compute. We don’t talk about the micro threads, the individual human stories as much, even though it is these individual human threads that cumulatively lead to the macro phenomenon. We should talk about these stories more! So that we can learn from each other, inspire each other. So we can be more robust; more effective in our endeavors. By strengthening our individual threads and our connections, we can weave a stronger fabric together. This talk is about some of my stories from my 20-year journey so far – about following up on all threads, about learnt reward functions, about fleeting opportunities, about multidimensional impact landscapes, and about curiosity for new experiences. It might seem narcissistic, but hopefully it will also feel authentic and vulnerable. And hopefully you will get something out of it.

Jie Tang, Tsinghua University

Talk Title: “The ChatGLM’s Road to AGI”

Abstract: Large language models have substantially advanced the state of the art in various AI tasks, such as natural language understanding and text generation, and image processing, multimodal modeling. In this talk, we will first introduce the development of AI in the past decades, in particular from the angle of China. We will also talk about the opportunities, challenges, and risks of AGI in the future. In the second part of the talk, we will use ChatGLM, an alternative but open-sourced model to ChatGPT, as an example to explain our understanding and insights derived during the implementation of the model.

The International Conference on Learning Representations (ICLR) is proud to announce the third edition of its pioneering Blogposts Track, a unique publication venue established in 2022 to address the lack of up-to-date educational material in the fast-paced field of Artificial Intelligence. The Blogposts Track aims to incentivize researchers to engage in reflective, critical discourse about existing work, offering insights, developing new intuitions, and highlighting potential shortcomings.

Building on the success of its inaugural year, which saw over 60 submissions and 20 accepted posts, the Blogposts Track continues to encourage the machine learning community to contribute to a more open and accessible exchange of ideas. By providing a formal venue for blog post publication, ICLR is taking a significant step towards democratizing knowledge dissemination in the field.

This year, 22 outstanding blog posts have been accepted for publication, each offering valuable perspectives on previously published papers. These posts, selected through a rigorous double-blind review process, cover a diverse range of topics and underscore the depth and breadth of contemporary machine learning research. They not only contribute to the ongoing dialogue within the community but also highlight the creative and pedagogical talent of their authors.

We are excited to highlight three submissions that exemplify the diversity and excellence of the contribution to the track this year:

• The N Implementation Details of RLHF with PPO – Revealing the many intricacies of RLHF, this post offers precious insights and fosters a deeper understanding of this new interactive learning paradigm.
• How to compute Hessian-vector products?– Exploring a ubiquitous computational aspect of optimization, this piece gives a clear and practical point of view on this problem.
• Bridging the Data Processing Inequality and Function-Space Variational Inference – Bridging information theory and practical aspects of Bayesian Deep Learning, this blog post gives valuable insights into predictive priors and their applications.

These posts not only highlight the broad spectrum of topics being explored in machine learning but also underscore the Blogposts Track’s commitment to fostering open, insightful, and high-quality scientific dialogue.

In line with the goal of promoting wider engagement and visibility, most of these blog posts will be presented as posters at the ICLR conference in Vienna from May 7th to May 11th during special “Affinity Posters” sessions. This presentation format will provide a unique opportunity for conference attendees to interact directly with the authors, allowing deeper discussions and potential collaborations.

All Blog Posts can be found on the Blog page of the track’s website.

Claire Vernade, Gauthier Gidel, Fabian Pedregosa, Charlie Gauthier, David Dobre, Leo Schwinn
Blogposts Track Program Chairs

By ICLR 2024 Workshop Chairs: Aisha Walcott-Bryant, Girmaw Abebe Tadesse, Luis Oala, Stephanie Muller and Mercy Asiedu

We thank everyone who prepared and submitted a workshop proposal to ICLR 2024. We were impressed by the quality of the proposals. This year, we received an unprecedented number of submissions, 103, and were able to accept 20 workshop proposals based on the number of available rooms in Vienna.

We also want to thank our team of reviewers, the ICLR program committee, and the ICLR 2024 Chairs for their kind support. 

Selection Process

Ultimately, we could only accept a limited number of proposals corresponding to the number of available rooms within the contracted venue. We worked to balance multiple goals. First and foremost, we relied on reviewer rankings of the workshops. Furthermore, we aimed to balance a good representation of theory, applications, and innovative multidisciplinary workshops to broaden the ICLR community. We also aimed to promote diversity across geography, gender, institutions, and seniority/juniority in the organization team and invited speakers. 

We are looking forward to supporting you in making your workshop a success – be it as an organizer, attendee, speaker or author. All workshops will be held on 11th May  2024. See you all in Vienna!

List of accepted workshops at ICLR 2024 (in no particular order)

Generative Models for Decision Making

5th Workshop on African Natural Language Processing (AfricaNLP 2024)

Integrating Generative and Experimental Platforms or Biomolecular Design

Workshop on Large Language Models for Agents

Machine Learning for Genomics Explorations (MLGenX)

Navigating and Addressing Data Problems for Foundation Models (DPFM)

2nd Workshop on Mathematical and Empirical Understanding of Foundation Models

Secure and Trustworthy Large Language Models

Data-centric Machine Learning Research (DMLR): Harnessing Momentum for Science

ICLR 2024 Workshop on Reliable and Responsible Foundation Models

Machine Learning for Remote Sensing (ML4RS)

Global AI Cultures

Tackling Climate Change with Machine Learning: Fostering the Maturity of ML Applications for Climate Change

Workshop on Learning from Time Series for Health

5th Workshop on practical ML for limited/low resource settings (PML4LRS) @ ICLR 2024

How Far Are We From AGI?

Bridging the Gap Between Practice and Theory in Deep Learning

First Workshop on Representational Alignment (Re-Align)

AI4DifferentialEquations In Science

(Virtual) Privacy Regulation and Protection in Machine Learning

1. Philosophy: why we do this

The year 2023 will be remembered as one where unprecedented and unparalleled advances on diversity, equity and inclusion (DEI) are made, by having a major machine learning conference successfully held in the African continent, for the first time in history. According to the Closing Remark, this simple change of location (while acknowledging that changes like this are never really simple) has resulted in a more than 13-fold increase (from 16 to 261) of African-based attendees.

As DEI Chairs this year, even though the majority of work pushing the DEI frontier was done when the conference location was decided, we still carry the responsibility of furthering the status quo. In January, the chairs (Rosanne, Krystal and Tom), with the support of the General Chair, Yan Liu, after meeting weekly for a few months, launched a Tiny Papers Track, an experimental paper submission track to welcome underrepresented, and non-traditional researchers into the ICLR community. As its name suggests, the track enforces a simplified format: no more than 2 pages of main content, to encourage the sharing of early results, pilot ideas, and preliminary findings.

Like any paper submission track, this effort involves putting out a call for submission, opening a submission portal, setting up a peer review system where reviewers, area chairs (ACs), and emergency reviewers and ACs are recruited, assigned tasks and consulted for decisions.

But unlike most paper tracks, we adopt an approach that embraces the principles of affirmative action, entailing the deliberate provision of advantages and preferences to historically disadvantaged populations. To that end, we ask every submission to include at least one key author that comes from a URM background, in terms of, for example, race, gender, age, geographical location, distability, or neurodiversity status. This involves adding a required section, an URM statement, to the paper submission, with an acknowledgment sentence that can be as simple as: The authors acknowledge that at least one key author of this work meets the URM criteria of the ICLR 2023 Tiny Papers Track. This honor system of self-identification respects individuals’ privacy and is aligned with a pluralistic view of advantage, representation, and systemic bias.

2. Practice: how we did this for ICLR 2023

The initiative was brainstormed, designed, and implemented for four months, before announcing to the world on January 23, 2023, and submission portal open February 1st, and submission deadline Feb 28th.

We received 219 submissions over a wide variety of topics. 580 unique total authors were involved in making submissions, with 526 of them making 1 submission, and 54 making 2 or more submissions.

We also recruited reviewers on the same day of the announcement. In the end, a total of 173 reviewers, 42 meta-reviewers (ACs) worked with us to ensure that all paper submissions have 3 or more reviews submitted. Reviewers asked to evaluate according to the CCR: Clear, Correct, & Reproducible criteria. Instead of the traditional “accept” or “reject” decision, we also adopt a novel categorization of decisions that consist of:

• Invite to present (notable)
• Invite to present
• Invite to archive
• Invite to revise

As the names suggest, those decisions reflect whether a submission meets the quality to be presented at our Tiny Papers Showcase Day, archived, or if it requires revision. Below is the distribution of the initial decision.

For those invited to revise, after revision they are given final decisions of either “Invite to archive” or “Not invite to archive”. 34 out of 58 (58.6%) submissions were changed categories from “Invite to revise” to “Invite to archive”. In the end, 194 of 219 (88.6%) submissions were accepted to archive. All archived papers can be found at DBLP.

On May 5, 2023, the last day of ICLR 2023, we hosted Tiny Papers Showcase Day, in Kigali, Rwanda. 86 papers and their authors were invited to give an oral presentation and/or poster presentation. It was a lovely day.

3. Prospect for 2024

Post-ICLR 2023, we received lots of inquiries: “Is Tiny Papers happening again? At ICLR or elsewhere?” Today, we can finally answer affirmatively, for ICLR 2024, to be held at Vienna, Austria.

We made a few changes this year to improve the program:

• Moved deadlines much earlier. An area for improvement for Tiny Papers 2023 was that it took too long to plan and we were left with too little time to execute. With such lessons learned, we moved this year’s deadlines months earlier. 
• Appointed dedicated Tiny Papers Chairs who will work with DEI chairs to ensure the success of this program.
• Shared deadlines and reviewer pool with blog post track. The blog post track has been running for 3 years and has demonstrated great success and momentum. It also has the same spirit of encouraging alternative formats of scientific publications. Therefore this year we are combining forces.

For more information, read the Call for Tiny Papers 2024. Hope to see your submissions there!

Thomas F Burns and Krystal Maughan
ICLR 2024 Tiny Papers Chairs

Rosanne Liu
ICLR 2023-2024 DEI Chair

ICLR has long been experimenting with the process of organizing its conferences. For example, recently ICLR joined NeurIPS and ICML in showcasing poster presentations of JMLR publications, through a joint Journal-to-Conference Track.

Today, the ICLR 2024 organizing committee and the TMLR Editors-in-Chief are happy to announce that authors of TMLR publications that have been given a Featured or Outstanding Certification are also invited to present their work in poster format at the upcoming ICLR conference in Vienna!

TMLR has successfully launched in 2022 and, with this initiative, ICLR is hoping to direct more attention to some of the most exciting work published by TMLR since then. This is executed as an experiment for 2024, that is separate from the NeurIPS/ICML/ICLR Journal-to-Conference Track (notably it does not concern NeurIPS or ICML).

Authors of eligible TMLR publications can submit a request to present through the following Google form: https://forms.gle/HcDpXs1JrwKx5kEd9 . 

The deadline to submit a request is January 17th 2024 EOD. 

With this experiment, we’re hoping to learn more about whether and how TMLR and ICLR should collaborate on highlighting and showcasing exciting research from the AI community.

For any questions, please contact iclr2024.programchairs@gmail.com.

Yisong Yue
ICLR 2024 Senior Program Chair

Swarat Chaudhuri, Katerina Fragkiadaki, Mohammad Emtiyaz Khan, Yizhou Sun
ICLR 2024 Program Chairs

Kyunghyun Cho, Raia Hadsell, Gautam Kamath, Hugo Larochelle
TMLR Editors-in-Chief