Jump to Content

-

ICML 2024

Vienna, Austria
Messe Wien Congress Center

View blog post

Google DeepMind is proud to be Diamond Sponsor for ICML 2024.

About ICML: The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning.

Organising Committee

  • Workshop Chair: Rebecca Roelofs
  • Diversity & Inclusion Chair: Alexander D'Amour

Showcase

Join us at the Google DeepMind booth in Hall B for the following sessions

Advancing Technical Fairness Research

Tuesday 23rd July: 10:00-10:30

Confused about the role of fairness research when developing "safe", "trustworthy" or "responsible" machine learning? Come and hear why we believe fairness remains an important societal and technical challenge, and how we are contributing to this field.

Run Gemini on your Laptop using Chrome

Tuesday 23rd July: 12:00-12:30

Want to see Gemini running on local hardware instead of a datacenter? Join our real time tech demo to watch a Gemini model running locally using Chrome on a laptop! Fast and high quality generations within the privacy of your machine. Then learn how to sign up and get it running on your own hardware.

AI for Education: LearnLM-Tutor

Tuesday 23rd July: 16:00-16:30

Following the recent Google I/O announcement of LearnLM, a new family of models, based on Gemini, and fine-tuned for learning, we will talk about the challenges and promises of fine-tuning Gemini for pedagogy and let you try out our LearnLM-Tutor.

Genie: Generative Interactive Environments

Wednesday 24th July: 10:00-10:30

We introduce Genie, a foundation world model trained from Internet videos that can generate an endless variety of playable (action-controllable) worlds from synthetic images, photographs, and even sketches.

Product Recontextualization With Imagen2

Wednesday 24th July: 12:00-12:30

How can GenAI empower advertisers to create new images showcasing their products without the need for costly and time consuming photoshoots? Come learn about how we combine a diffusion text-to-image model with DreamBooth finetuning to solve the challenge of preserving objects' fidelity while rendering them in novel contexts.

TacticAI: an AI Assistant for Football Tactics

Wednesday 24th July: 16:00-16:30

Identifying key patterns of tactics implemented by rival teams, and developing effective responses, lies at the heart of modern football. However, doing so algorithmically remains an open research challenge. To address this unmet need, we propose TacticAI, an AI football tactics assistant developed and evaluated in close collaboration with domain experts from Liverpool FC.

Meet the Talent Acquistion Team

Tuesday 23rd July: 14:00-15:00

Wednesday 24th July: 14:00-15:00

Join Google DeepMinds Talent Acquisition team if you want to learn about hiring locations and current open roles. Come and ask questions about what we look for in CV's, interview preparation guidance as well as other general tips and tricks for applying to roles.

Sessions

Discover the affinity groups we're partnering with to build a more supportive and inclusive space

Women in Machine Learning (WiML)

Social

We’re supporting the WiML community in increasing awareness and appreciation of the achievements of women in machine learning.

More about WiML

Queer in AI

Social

We’re supporting the Queer in AI community in raising awareness of queer issues in AI/ML and celebrate the work of queer scientists

More about QueerinAI

LatinX in AI

Social

We’re supporting LatinX in AI (LXAI) to foster a thriving community of LatinX professionals in AI, ML, and data science through research, mentorship, and advocacy

More about LXAI

Research

Explore our papers at ICML 2024

A Distributional Analogue to the Successor Representation

Harley Wiltzer · Jesse Farebrother · Arthur Gretton · Yunhao Tang · Andre Barreto · Will Dabney · Marc Bellemare · Mark Rowland

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #1405

View Paper

A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

Nicholas Monath · Will Grathwohl · Michael Boratko · Rob Fergus · Andrew McCallum · Manzil Zaheer
Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #911

View Paper

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

Kuang-Huei Lee · Xinyun Chen · Hiroki Furuta · John Canny · Ian Fischer

Poster: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #802

View Paper

A Large Language Model walks into a psychology lab

Julian Coda-Forno · Marcel Binz · Jane Wang · Eric Schulz

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #717

View Paper

Adaptive Accompaniment with ReaLchords

Yusong Wu · Tim Cooijmans · Kyle Kastner · Adam Roberts · Ian Simon · Alexander Scarlatos · Chris Donahue · Cassie Tarakajian · Shayegan Omidshafiei · Aaron Courville · Pablo Samuel Castro · Natasha Jaques · Cheng Zhi Huang

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #515

View Paper

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Yifei Zhou · Andrea Zanette · Jiayi Pan · Sergey Levine · Aviral Kumar

Poster: Wed. 24 Jul, 1:30 - 3:00, Hall C 4-9 #515

View Paper

Assessing LLMs on Climate Information

Jannis Bulian · Mike Schäfer · Afra Amini · Heidi Lam · Massimiliano Ciaramita · Ben Gaiarin · Michelle Chen Huebscher · Christian Buck · Niels Mede · Markus Leippold · Nadine Strauss

Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #612

View Paper

Auditing Private Prediction

Karan Chadha · Matthew Jagielski · Nicolas Papernot · Christopher A. Choquette Choo · Milad Nasresfahani

Poster: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #2315

View Paper

BAGEL: Bootstrapping Agents by Guiding Exploration with Language

Shikhar Murty · Christopher Manning · Peter Shaw · Mandar Joshi · Kenton Lee

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #2610

View Paper

Chain of Code Prompting and Execution: Leveraging Code as Reasoning for Large Language Models

Chengshu Li · Jacky Liang · Andy Zeng · Xinyun Chen · Karol Hausman · Dorsa Sadigh · Sergey Levine · Li Fei-Fei · Fei Xia · brian ichter

Oral: Wed 24 Jul 11:30 - 1:00

Poster: Wed 24 Jul 10:30 - 11:30, Hall C 4-9 #2809

View Paper

Controlled Decoding from Language Models

Sidharth Mudgal · Jong Lee · Harish Ganapathy · YaGuang Li · Tao Wang · Yanping Huang · Zhifeng Chen · Heng-Tze Cheng · Michael Collins · Trevor Strohman · Jilin Chen · Alex Beutel · Ahmad Beirami

Poster: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #2712

View Paper

Decoding-time Realignment of Language Models

Tianlin Liu · Shangmin Guo · Leonardo Bianco · Daniele Calandriello · Quentin Berthet · Felipe Llinares-Lopez · Jessica Hoffmann · Lucas Dixon · Michal Valko · Mathieu Blondel

Spotlight: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #916

View Paper

Denoising Autoregressive Models for Visual Representation Learning

Yazhe Li · Jorg Bornschein · Ting Chen

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #1005

View Paper

Distributional Bellman Operators over Mean-embeddings

Li Kevin Wenliang · Gregoire Deletang · Matthew Aitchison · Marcus Hutter · Anian Ruoss · Arthur Gretton · Mark Rowland
Poster: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #1315

View Paper

Don't trust your eyes: on the (un)reliability of feature visualizations

Robert Geirhos · Roland S. Zimmermann · Blair Bilodeau · Wieland Brendel · Been Kim

Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #2213

View Paper

Evaluating model bias requires characterizing its mistakes

Isabela Albuquerque · Jessica Schrouff · David Warde-Farley · Taylan Cemgil · Sven Gowal · Olivia Wiles

Poster: Thu, 25 Jul, 1:30 - 3:00, Hall C 4-9 #2307

View Paper

Evaluating Truthfulness and Relevance in Large Language Models

Ryan Liu · Theodore R Sumers · Ishita Dasgupta · Thomas Griffiths

Oral: Wed, 24 Jul, 1:30 - 3:00 , Oral 4E LLMs

Poster: Wed, 24 Jul, 4:30 - 6:00, Hall C 4-9 #2217

View Paper

Experts Don't Cheat: Learning What You Don't Know by Predicting Pairs

Daniel D. Johnson · Daniel Tarlow · David Duvenaud · Chris Maddison

Poster: Wed, 24 Jul, 1:30 -3:00, Hall C 4-9 #1005

View Paper

Exploration at Scale using Epistemic Neural Networks

Vikranth Dwaracherla · Seyed Mohammad Asghari · Botao Hao · Benjamin Van Roy

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #714

View Paper

FrameQuant: Flexible Low-Bit Quantization for Transformers

Harshavardhan Adepu, Zhanpeng Zeng, Li Zhang, Vikas Singh

Paper: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #808

View Paper

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything

Alexandru Tifrea, Preethi Lahoti, Ben Packer, Yoni Halpern, Ahmad Beirami, Flavien Prost

Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #2217

View Paper

Generalized preference optimization: a unified approach to offline alignment

Yunhao Tang · Zhaohan Guo · Zeyu Zheng · Daniele Calandriello · REMI MUNOS · Mark Rowland · Pierre Richemond · Michal Valko · Bernardo Avila Pires · Bilal Piot

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #905

View Paper

Genie: Generative Interactive Environments

Jake Bruce · Michael Dennis · Ashley Edwards · Jack Parker-Holder · Yuge Shi · Edward Hughes · Matthew Lai · Aditi Mavalankar · Richie Steigerwald · Chris Apps · Yusuf Aytar · Sarah Bechtle · Feryal Behbahani · Stephanie Chan · Nicolas Heess · Lucy Gonzalez · Simon Osindero · Sherjil Ozair · Scott Reed · Jingwei Zhang · Konrad Zolna · Jeff Clune · Nando de Freitas · Satinder Singh · Tim Rocktäschel

Oral: Tue, 23 Jul, 11:30 - 1:00, Oral 1D Video

Poster: Tue, 23 Jul, 10:30 - 11:30, Hall C 4-9 #614

View Paper

Human Alignment of Large Language Models through Online Preference Optimisation

Daniele Calandriello · Zhaohan Guo · REMI MUNOS · Mark Rowland · Yunhao Tang · Bernardo Avila Pires · Pierre Richemond · Charline Le Lan · Michal Valko · Tianqi Liu · Rishabh Joshi · Zeyu Zheng · Bilal Piot

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #502

View Paper

Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements

Naman Agarwal · Satyen Kale · Karan Singh · Abhradeep Guha Thakurta

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #2401

View Paper

Improving fine-grained understanding in image-text pre-training

Ioana Bica · Anastasija Ilic · Matthias Bauer · Goker Erdogan · Matko Bošnjak · Christos Kaplanis · Alexey Gritsenko · Matthias Minderer · Charles Blundell · Razvan Pascanu · Jovana Mitrovic Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #708

View Paper

In value-based deep reinforcement learning, a pruned network is a good network

Johan Obando Ceron · Aaron Courville · Pablo Samuel Castro

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #1308

View Paper

In-Context Principle Learning from Mistakes

Tianjun Zhang · Aman Madaan · Luyu Gao · Steven Zheng · Swaroop Mishra · Yiming Yang · Niket Tandon · Uri Alon

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #2701

View Paper

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization

Idan Attias · Gintare Karolina Dziugaite · Mahdi Haghifam · Roi Livni · Daniel Roy

Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #2400 Oral: Thu, 25 Jul, 10:30 -11:30, Oral 5B Optimization 2

View Paper

Interpretability Illusions in the Generalization of Simplified Models

Dan Friedman, Andrew Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #2405

View Paper

Learning Planning-compatible Cognitive Maps with Transformers in PartiallyObserved Environments

Antoine Dedieu · Wolfgang Lehrach · Guangyao Zhou · Dileep George · Miguel Lazaro-Gredilla

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #812

View Paper

Learning Universal Predictors

Jordi Grau-Moya · Tim Genewein · Marcus Hutter · Laurent Orseau · Gregoire Deletang · Elliot Catt · Anian Ruoss · Li Kevin Wenliang · Christopher Mattern · Matthew Aitchison · Joel Veness

Poster: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #2208

View Paper

Levels of AGI for Operationalizing Progress on the Path to AGI

Meredith Morris · Jascha Sohl-Dickstein · Noah Fiedel · Tris Warkentin · Allan Dafoe · Aleksandra Faust · Clement Farabet · Shane Legg

Spotlight: Tue, 23 Jul, 11:30 -1:00, Hall C 4-9 #2306

View Paper

Leveraging VLM-Based Pipelines to Annotate 3D Objects

Rishabh Kabra · Loic Matthey · Alexander Lerchner · Niloy Mitra

Poster: Thu, 25 Jul, 1:30 - 3:00, Hall C 4-9 #107

View Paper

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views

Yuji Roh · Qingyun Liu · Huan Gui · Zhe Yuan · Yujin Tang · Steven Whang · Liang Liu · Shuchao Bi · Lichan Hong · Ed Chi · Zhe Zhao

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #1006

View Paper

Mechanism Comparisons in Differential Privacy

Georgios Kaissis · Stefan Kolek · Borja de Balle Pigem · Jamie Hayes · Daniel Rueckert

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #2209

View Paper

Memory Consolidation Enables Long-Context Video Understanding

Ivana Balazevic · Yuge Shi · Pinelopi Papalampidi · Rahma Chaabouni · Skanda Koppula · Olivier Henaff

Spotlight: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #2212

View Paper

Mixtures of Experts Unlock Parameter Scaling for Deep RL

Johan Obando Ceron · Ghada Sokar · Timon Willi · Clare Lyle · Jesse Farebrother · Jakob Foerster · Gintare Karolina Dziugaite · Doina Precup · Pablo Samuel Castro

Spotlight: Thu, 25 Jul, 1:30 - 3:00, Hall C 4-9 #1207

View Paper

MusicRLHF: Improving MusicLM models with Reinforcement Learning from Human Feedback

Geoffrey Cideron · Sertan Girgin · Mauro Verzetti · Damien Vincent · Matej Kastelic · Zalán Borsos · Brian McWilliams · Victor Ungureanu · Olivier Bachem · Olivier Pietquin · Matthieu Geist · Léonard Hussenot · Neil Zeghidour · Andrea Agostinelli

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #1203

View Paper

Nash Learning from Human Feedback

REMI MUNOS · Michal Valko · Daniele Calandriello · Mohammad Gheshlaghi Azar · Mark Rowland · Zhaohan Guo · Yunhao Tang · Matthieu Geist · Thomas Mesnard · Côme Fiegel · Andrea Michi · Marco Selvi · Sertan Girgin · Nikola Momchev · Olivier Bachem · Daniel Mankowitz · Doina Precup · Bilal Piot

Spotlight: Thu, 25 Jul, 1:30 -3:00, Hall C 4-9 #708

View Paper

NExT: Teaching Large Language Models to Reason about Code Execution

Ansong Ni · Miltiadis Allamanis · Arman Cohan · Yinlin Deng · Kensen Shi · Charles Sutton · Pengcheng Yin

Poster: Wed, 24 Jul, 1:30 - 3:00

View Paper

Offline Actor-Critic Reinforcement Learning Scales to Large Models

Jost Springenberg · Abbas Abdolmaleki · Jingwei Zhang · Oliver M Groth · Michael Bloesch · Thomas Lampe · Philemon Brakel · Sarah Bechtle · Steven Kapturowski · Roland Hafner · Nicolas Heess · Martin Riedmiller

Oral : Wed, 24 Jul, 4:30 - 5:30, Oral 4A Reinforcement Learning 2

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #2707

View Paper

Open-Endedness is Necessary for Artificial Superhuman Intelligence

Edward Hughes · Michael Dennis · Jack Parker-Holder · Feryal Behbahani · Aditi Mavalankar · Yuge Shi · Tom Schaul · Tim Rocktäschel

Oral: Thu, 25 Jul, 4:30 - 5:30, Oral 6A Agents and World Modeling

Poster: Thu, 25 Jul, 1:30 - 3:00, Hall C 4-9 #613

View Paper

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva

Poster: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #2410

View Paper

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Soroush Nasiriany · Fei Xia · Wenhao Yu · Ted Xiao · Jacky Liang · Ishita Dasgupta · Annie Xie · Danny Driess · Ayzaan Wahid · Zhuo Xu · Quan Vuong · Tingnan Zhang · Tsang-Wei Lee · Kuang-Huei Lee · Peng Xu · Sean Kirmani · Yuke Zhu · Andy Zeng · Karol Hausman · Nicolas Heess · Chelsea Finn · Sergey Levine · brian ichter

Poster: Tue, 23 Jul, 1:30 - 3:00

View Paper

Position Paper: Video Generation for Decision Making

Sherry Yang · Jacob C Walker · Jack Parker-Holder · Yilun Du · Jake Bruce · Andre Barreto · Pieter Abbeel · Dale Schuurmans

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #601

View Paper

Position: Categorical Deep Learning is an Algebraic Theory of All Architectures

Bruno Gavranović · Paul Lessard · Andrew Dudzik · Tamara von Glehn · João Madeira Araujo · Petar Veličković

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #1110

View Paper

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining

Florian Tramer · Gautam Kamath · Nicholas Carlini Oral: Tue, 23 Jul, 11:00 - 11:15, Oral 1B Positions on How We Do Machine Learning Research

Poster: Tue, 23 Jul, 11:30 - 1:00

View Paper

Position: Leverage Foundational Models for Black-Box Optimization

Xingyou Song · Yingtao Tian · Robert Lange · Chansoo Lee · Yujin Tang · Yutian Chen

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #1105

View Paper

Position: Topological Deep Learning is the New Frontier for Relational Learning

Theodore Papamarkou · Tolga Birdal · Michael Bronstein · Gunnar Carlsson · Justin Curry · Yue Gao · Mustafa Hajij · Roland Kwitt · Pietro Lió · Paolo Di Lorenzo · Vasileios Maroulas · Nina Miolane · Farzana Nasrin · Karthikeyan Ramamurthy · Bastian Rieck · Simone Scardapane · Michael Schaub · Petar Veličković · Bei Wang · Yusu Wang · Guowei Wei · Ghada Zam

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #307

View Paper

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Feedback

Andi Peng · Yuying Sun · Tianmin Shu · David Abel

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #1302

View Paper

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Fahim Tajwar, Anikait Singh, Archit Sharma, Rafael Rafailov, Jeff Schneider, Tengyang Xie, Stefano Ermon, Chelsea Finn, Aviral Kumar

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #912

View Paper

Premise Order Matters in Reasoning with Large Language Models

Xinyun Chen · Ryan Chi · Xuezhi Wang · Denny Zhou

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #601

View Paper

Private Gradient Descent for Linear Regression: Tighter Error Bounds andInstance-Specific Uncertainty Estimation

Gavin Brown · Krishnamurthy Dvijotham · Georgina Evans · Daogao Liu · Adam Smith · Abhradeep Guha Thakurta

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #2816

View Paper

Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution

Chrisantha Fernando · Dylan Banarse · Henryk Michalewski · Simon Osindero · Tim Rocktäschel

Poster: Thu, 25 Jul, 1:30 - 3:00, Hall C 4-9 #611

View Paper

Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning

Hongming Zhang · Tongzheng Ren · Chenjun Xiao · Dale Schuurmans · Bo Dai

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #2816

View Paper

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, Sushant Prakash

Poster: Thu. 25 Jul. 1:30 - 3:00

View Paper

Robust Inverse Graphics via Probabilistic Inference

Tuan Anh Le, Pavel Sountsov, Matthew D. Hoffman, Ben Lee, Brian Patton, Rif A. Saurous

Paper: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #1413

View Paper

Rolling Diffusion Models

David Ruhe · Jonathan Heek · Tim Salimans · Emiel Hoogeboom

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #409

View Paper

Scalable AI Safety via Doubly-Efficient Debate

Jonah Brown-Cohen · Geoffrey Irving · Georgios Piliouras

Oral: Thu, 25 Jul, 4:30 - 5:30, Oral 6E Robustness and Safety Poster:

Thu, 25 Jul 1:30: - 3:00, Hall C 4-9 #1405

View Paper

Scaling Exponents Across Parameterizations and Optimizers

Katie Everett · Lechao Xiao · Mitchell Wortsman · Alexander Alemi · Roman Novak · Peter Liu · Izzeddin Gur · Jascha Sohl-Dickstein · Leslie Kaelbling · Jaehoon Lee · Jeffrey Pennington

Poster: Tue, 23 Jul, 1:30 - 3:00, Hall C 4-9 #2500

View Paper

Self-Correcting Self-Consuming Loops for Generative Model Training

Nate Gillman, Michael Freeman, Daksh Aggarwal, Chia-Hong Hsu, Calvin Luo, Yonglong Tian, Chen Sun

Paper: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #1413

View Paper

SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning

Matthias Weissenbacher, Rishabh Agarwal, Yoshinobu Kawahara

Poster: Wed, 24 Jul, 11:30 - 1:00 , Hall C 4-9 #1302

View Paper

Stealing part of a production language model

Nicholas Carlini · Daniel Paleka · Krishnamurthy Dvijotham · Thomas Steinke · Jonathan Hayase · A. Feder Cooper · Katherine Lee · Matthew Jagielski · Milad Nasresfahani · Arthur Conmy · Eric Wallace · David Rolnick · Florian Tramer

Oral: Wed, 24 Jul, 4:30 - 4:45, Oral 4C Safety and Control

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall A2

View Paper

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Jesse Farebrother · Jordi Orbay · Quan Vuong · Adrien Ali Taiga · Yevgen Chebotar · Ted Xiao · Alexander Irpan · Sergey Levine · Pablo Samuel Castro · Aleksandra Faust · Aviral Kumar · Rishabh Agarwal

Oral: Wed, 24 Jul, 4:30 - 5:30, Oral 4A Reinforcement Learning 2

Poster: Wed, 24 Jul, 1:30 - 3:00, Hall C 4-9 #1311

View Paper

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation

Fengdi Che · Chenjun Xiao · Jincheng Mei · Bo Dai · Ramki Gummadi · Oscar Ramirez · Christopher Harris · Rupam Mahmood · Dale Schuurmans

Spotlight: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #1309

View Paper

The Role of Forgetting in Fine-Tuning Reinforcement Learning Models

Maciej Wołczyk · Bartłomiej Cupiał · Mateusz Ostaszewski · Michał Bortkiewicz · Michał Zając · Razvan Pascanu · Lukasz Kucinski · Piotr Milos

Spotlight: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #1410

View Paper

Transforming and Combining Rewards for Aligning Large Language Models

Zihao Wang · Chirag Nagpal · Jonathan Berant · Jacob Eisenstein · Alexander D'Amour · Sanmi Koyejo · Victor Veitch

Poster: Wed, 24 Jul, 11:30 -1:00, Hall C 4-9 #2710

View Paper

Unsupervised Evaluation of Code LLMs with Round-Trip Correctness

Miltiadis Allamanis · Sheena Panthaplackel · Pengcheng Yin

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #913

View Paper

VideoPoet: A Large Language Model for Zero-Shot Video Generation

Dan Kondratyuk* · Lijun Yu* · Xiuye Gu* · José Lezama* · Jonathan Huang* · Grant Schindler · Rachel Hornung · Vighnesh Birodkar · Jimmy Yan · Ming-Chang Chiu · Krishna Somandepalli · Hassan Akbari · Yair Alon · Yong Cheng · Josh Dillon · Agrim Gupta · Meera Hahn · Anja Hauth · David Hendon · Alonso Martinez · David Minnen · Mikhail Sirotenko · Kihyuk Sohn · Xuan Yang · Hartwig Adam · Ming-Hsuan Yang · Irfan Essa · Huisheng Wang · David A. Ross · Bryan Seybold* · Lu Jiang*

Oral: Tue, 23 Jul, 11:15 - 11:30, Oral 1D Video

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall A8

View Paper

VideoPrism: A Foundational Visual Encoder for Video Understanding

Long Zhao · Nitesh Bharadwaj Gundavarapu · Liangzhe Yuan · Hao Zhou · Shen Yan · Jennifer J. Sun · Luke Friedman · Rui Qian · Tobias Weyand · Yue Zhao · Rachel Hornung · Florian Schroff · Ming-Hsuan Yang · David Ross · Huisheng Wang · Hartwig Adam · Mikhail Sirotenko · Ting Liu · Boqing Gong

Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #205

View Paper

WARM: On the Benefits of Weight Averaged Reward Models

Alexandre Rame · Nino Vieillard · Léonard Hussenot · Robert Dadashi · Geoffrey Cideron · Olivier Bachem · Johan Ferret

Poster: Tue, 23 Jul, 11:30 - 1:00, Hall C 4-9 #913

View Paper

What makes an image realistic?

Lucas Theis

Spotlight: Wed, 24 Jul, 11:30 - 1:00, Hall C 4-9 #2714

View Paper

What needs to go right for an induction head?

Aaditya Singh · Ted Moskovitz · Feilx Hill · Stephanie Chan · Andrew Saxe

Spotlight: Wed, 24 Ju,l 11:30 - 1:00, Hall C 4-9 #407

View Paper

When Linear Attention Meets Autoregressive Decoding: An Empirical Study of Linearized Large Language Models

Haoran You · Yichao Fu · Zheng Wang · Amir Yazdanbakhsh · Yingyan (Celine) Lin

Poster: Thu, 25 Jul, 11:30 - 1:00, Hall C 4-9 #603

View Paper