ICML

Robust Yet Efficient Conformal Prediction Sets

Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski

Comments Proceedings of the 41st International Conference on Machine Learning

Characterizing Prompt Compression Methods for Long Context Inference

Siddharth Jha, Lutfi Eren Erdogan, Sehoon Kim, Kurt Keutzer, Amir Gholami

Comments Es-FoMo @ ICML 2024

Proving that Cryptic Crossword Clue Answers are Correct

Martin Andrews, Sam Witteveen

Comments Accepted paper for the ICML 2024 Workshop on LLMs and Cognition (4 pages + references + 6 pages of Appendices)

Federated Learning and AI Regulation in the European Union: Who is Responsible? -- An Interdisciplinary Analysis

Herbert Woisetschläger, Simon Mertel, Christoph Krönke, Ruben Mayer, Hans-Arno Jacobsen

Comments Accepted at the GenLaw'24 workshop in conjunction with ICML'24

Structured Generations: Using Hierarchical Clusters to guide Diffusion Models

Jorge da Silva Goncalves, Laura Manduchi, Moritz Vandenhirtz, Julia E. Vogt

Comments 8 pages, 7 figures, Structured Probabilistic Inference & Generative Modeling workshop of ICML 2024

Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning

Yizhe Huang, Anji Liu, Fanqi Kong, Yaodong Yang, Song-Chun Zhu, Xue Feng

Comments Accepted at ICML 2024

Chasing Convex Functions with Long-term Constraints

Adam Lechowicz, Nicolas Christianson, Bo Sun, Noman Bashir, Mohammad Hajiesmaili, Adam Wierman, Prashant Shenoy

Comments Accepted to ICML 2024. 31 pages, 12 figures

Challenges in Mechanistically Interpreting Model Representations

Satvik Golechha, James Dao

Comments 9 pages, ICML 2024 Workshop on Mechanistic Interpretability

Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time

Sungyoon Kim, Mert Pilanci

Comments Version 2: Fixed proof of Thm 4.4, slight clarification on assumption 2 Version 3: Modified to ICML style and slight clarification on assumption 1

Enhancing Transformer RNNs with Multiple Temporal Perspectives

Razvan-Gabriel Dumitru, Darius Peteleaza, Mihai Surdeanu

Comments 13 pages, 8 figures, 4 tables, accepted at ICML 2024 - Next Generation of Sequence Modeling Architectures workshop

Extracting Training Data from Document-Based VQA Models

Francesco Pinto, Nathalie Rauschmayr, Florian Tramèr, Philip Torr, Federico Tombari

Comments ICML 2024

Reducing Uncertainty Through Mutual Information in Structural and Systems Biology

Vincent D. Zaballa, Elliot E. Hui

Comments Accepted at the 1st Machine Learning for Life and Material Sciences Workshop at ICML 2024

Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation

Björn Nieth, Thomas Altstidl, Leo Schwinn, Björn Eskofier

Comments 8 pages, 5 figures, 3 tables, to be published in ICML: DMLR workshop

Parallelizing Autoregressive Generation with Variational State Space Models

Gaspard Lambrechts, Yann Claes, Pierre Geurts, Damien Ernst

Comments 4 pages, 11 pages total, 3 figures

Journal ref ICML Workshop on Next Generation of Sequence Modeling Architectures, 2024

Gaussian process interpolation with conformal prediction: methods and comparative analysis

Aurélien Pion, Emmanuel Vazquez

Journal ref LOD 2024, 10th International Conference on Machine Learning, Optimization, and Data Science, Sep 2024, Castiglione della Pescaia Grosseto Italy, Italy

Position: Measure Dataset Diversity, Don't Just Claim It

Dora Zhao, Jerone T. A. Andrews, Orestis Papakyriakopoulos, Alice Xiang

Comments ICML 2024 (Position Paper Track)

AND: Audio Network Dissection for Interpreting Deep Acoustic Models

Tung-Yu Wu, Yu-Xiang Lin, Tsui-Wei Weng

Comments Accepted by ICML'24

Journal ref Forty-first International Conference on Machine Learning (2024)

Image Fusion via Vision-Language Model

Zixiang Zhao, Lilun Deng, Haowen Bai, Yukun Cui, Zhipeng Zhang, Yulun Zhang, Haotong Qin, Dongdong Chen, Jiangshe Zhang, Peng Wang, Luc Van Gool

Comments Accepted by International Conference on Machine Learning (ICML) 2024

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

Dake Zhang, Boxiang Lyu, Shuang Qiu, Mladen Kolar, Tong Zhang

Comments ICML 2024

Inference Performance Optimization for Large Language Models on CPUs

Pujiang He, Shan Zhou, Wenhuan Huang, Changqing Li, Duyi Wang, Bin Guo, Chen Meng, Sheng Gui, Weifei Yu, Yi Xie

Comments 5 pages, 6 figure, ICML 2024 on Foundation Models in the Wild

Amazing Things Come From Having Many Good Models

Cynthia Rudin, Chudi Zhong, Lesia Semenova, Margo Seltzer, Ronald Parr, Jiachang Liu, Srikar Katta, Jon Donnelly, Harry Chen, Zachery Boner

Journal ref ICML (spotlight), 2024

Domain-Aware Fine-Tuning of Foundation Models

Ugur Ali Kaplan, Margret Keuper, Anna Khoreva, Dan Zhang, Yumeng Li

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

Mitigating Bias in Dataset Distillation

Justin Cui, Ruochen Wang, Yuanhao Xiong, Cho-Jui Hsieh

Comments ICML

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies

Brian R. Bartoldson, James Diffenderfer, Konstantinos Parasyris, Bhavya Kailkhura

Comments ICML 2024

A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models

Sebastian G. Gruber, Florian Buettner

Comments Published at ICML 2024: https://openreview.net/pdf?id=QwgSOwynxD

Self-Organising Neural Discrete Representation Learning à la Kohonen

Kazuki Irie, Róbert Csordás, Jürgen Schmidhuber

Comments Two first authors. Accepted to ICANN 2024. The Version of Record of this contribution is published by Springer. An earlier version was presented at ICML 2023 Workshop on Sampling and Optimization in Discrete Space (SODS)

Potential Based Diffusion Motion Planning

Yunhao Luo, Chen Sun, Joshua B. Tenenbaum, Yilun Du

Comments ICML 2024. Project page and code at https://energy-based-model.github.io/potential-motion-plan/

OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos

Ziyang Song, Jinxi Li, Bo Yang

Comments ICML 2024. Code and data are available at: https://github.com/vLAR-group/OSN

Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization

Liam Schramm, Abdeslam Boularias

Comments To be published in ICML 2024 Conference Proceedings

Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients

Mengmeng Ma, Tang Li, Xi Peng

Comments ICML 2024