ICML

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems

Jianliang He, Siyu Chen, Fengzhuo Zhang, Zhuoran Yang

Comments 47 pages, accepted by ICML 2024

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data

Giannis Daras, Alexandros G. Dimakis, Constantinos Daskalakis

Comments Accepted to ICML 2024

Representing Molecules as Random Walks Over Interpretable Grammars

Michael Sun, Minghao Guo, Weize Yuan, Veronika Thost, Crystal Elaine Owens, Aristotle Franklin Grosz, Sharvaa Selvan, Katelyn Zhou, Hassan Mohiuddin, Benjamin J Pedretti, Zachary P Smith, Jie Chen, Wojciech Matusik

Journal ref ICML 2024

Structure Your Data: Towards Semantic Graph Counterfactuals

Angeliki Dimitriou, Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas, Giorgos Stamou

Journal ref ICML 2024

xT: Nested Tokenization for Larger Context in Large Images

Ritwik Gupta, Shufan Li, Tyler Zhu, Jitendra Malik, Trevor Darrell, Karttikeya Mangalam

Comments Accepted to the 2024 International Conference on Machine Learning (ICML)

Position: Insights from Survey Methodology can Improve Training Data

Stephanie Eckman, Barbara Plank, Frauke Kreuter

Comments 9 pages, 4 figures. ICML 2024 Position Paper, forthcoming

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12268-12283, 2024

D-Flow: Differentiating through Flows for Controlled Generation

Heli Ben-Hamu, Omri Puny, Itai Gat, Brian Karrer, Uriel Singer, Yaron Lipman

Comments ICML 2024

Stochastic optimization with arbitrary recurrent data sampling

William G. Powell, Hanbaek Lyu

Comments 39 pages, 4 figures, 1 table

Journal ref International Conference on Machine Learning, 2024

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

Doyoung Kim, Susik Yoon, Dongmin Park, Youngjun Lee, Hwanjun Song, Jihwan Bang, Jae-Gil Lee

Comments ICML 2024

VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency

Vernon Toh Yan Han, Ratish Puduppully, Nancy F. Chen

Comments AI4MATH Workshop @ ICML 2024

Interacting Diffusion Processes for Event Sequence Forecasting

Mai Zeng, Florence Regol, Mark Coates

Comments camera ready version for ICML

Gibbs Sampling of Continuous Potentials on a Quantum Computer

Arsalan Motamedi, Pooya Ronagh

Comments 50 pages, version accepted in ICML 2024 / PMLR

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36322-36371, 2024

MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective

Yizhuo Chen, Chun-Fu Chen, Hsiang Hsu, Shaohan Hu, Marco Pistoia, Tarek Abdelzaher

Comments ICML 2024, GitHub: https://github.com/jpmorganchase/MaSS

Discovering environments with XRM

Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim, Nicolas Ballas, Pascal Vincent, David Lopez-Paz

Comments Oral at ICML 2024

GLAudio Listens to the Sound of the Graph

Aurelio Sulser, Johann Wenckstern, Clara Kuempel

Journal ref ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learning and Generative Modeling

LinSATNet: The Positive Linear Satisfiability Neural Networks

Runzhong Wang, Yunhao Zhang, Ziao Guo, Tianyi Chen, Xiaokang Yang, Junchi Yan

Comments This is a revised version of our ICML'23 publication that fixes a minor issue in Eq (11). In Proceedings of the 40th International Conference on Machine Learning (ICML'23)

Generative Model for Small Molecules with Latent Space RL Fine-Tuning to Protein Targets

Ulrich A. Mbou Sob, Qiulin Li, Miguel Arbesú, Oliver Bent, Andries P. Smit, Arnu Pretorius

Comments 12 pages, 6 figures, Proceedings of the ICML 2024 Workshop on Accessible and Effi- cient Foundation Models for Biological Discovery, Vienna, Austria. 2024

Robust Multi-Task Learning with Excess Risks

Yifei He, Shiji Zhou, Guojun Zhang, Hyokun Yun, Yi Xu, Belinda Zeng, Trishul Chilimbi, Han Zhao

Comments ICML 2024 camera-ready version

SPADE: Sparsity-Guided Debugging for Deep Neural Networks

Arshia Soltani Moakhar, Eugenia Iofinova, Elias Frantar, Dan Alistarh

Comments Published at ICML 2024. 33 pages

Predicting dark matter halo masses from simulated galaxy images and environments

Austin J. Larson, John F. Wu, Craig Jones

Comments 11 pages, 3 figures, accepted to ICML 2024 AI4Science Workshop

Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information

Fedor Sergeev, Paola Malsot, Gunnar Rätsch, Vincent Fortuin

Comments Presented at the ICML 2024 Next Generation of Sequence Modeling Architectures (NGSM) Workshop

Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction

Riccardo De Santi, Federico Arangath Joseph, Noah Liniger, Mirco Mutti, Andreas Krause

Comments ICML 2024

Integrated Hardware Architecture and Device Placement Search

Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan

Comments Accepted at the 41st International Conference on Machine Learning (ICML), 2024

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks

Antoni Kowalczuk, Jan Dubiński, Atiyeh Ashari Ghomi, Yi Sui, George Stein, Jiapeng Wu, Jesse C. Cresswell, Franziska Boenisch, Adam Dziedzic

Comments Accepted at the ICML 2024 Workshop on Foundation Models in the Wild

Federated Representation Learning in the Under-Parameterized Regime

Renpu Liu, Cong Shen, Jing Yang

Comments This work has been accepted to ICML 2024

Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models

Akhil Kedia, Mohd Abbas Zaidi, Sushil Khyalia, Jungho Jung, Harshith Goka, Haejun Lee

Comments Accepted at ICML 2024. Source code is available at https://github.com/akhilkedia/TranformersGetStable. Akhil Kedia, Mohd Abbas Zaidi, Sushil Khyalia equal contribution

Feedback Efficient Online Fine-Tuning of Diffusion Models

Masatoshi Uehara, Yulai Zhao, Kevin Black, Ehsan Hajiramezanali, Gabriele Scalia, Nathaniel Lee Diamant, Alex M Tseng, Sergey Levine, Tommaso Biancalani

Comments Accepted at ICML 2024

QuRating: Selecting High-Quality Data for Training Language Models

Alexander Wettig, Aatmik Gupta, Saumya Malik, Danqi Chen

Comments Accepted at ICML 2024. The results for top-k selection have been corrected. The code, models and data are available at https://github.com/princeton-nlp/QuRating

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

Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy

Comments 41 Pages, To appear in ICML 2024

Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture

Sangjun Park, JinYeong Bak

Comments ICML 2024 Spotlight. 29 pages, 15 figures, 11 tables

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39587-39615, 2024