ICML

Assessing Large Language Models on Climate Information

Jannis Bulian, Mike S. Schäfer, Afra Amini, Heidi Lam, Massimiliano Ciaramita, Ben Gaiarin, Michelle Chen Hübscher, Christian Buck, Niels G. Mede, Markus Leippold, Nadine Strauß

Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML), 2024

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate

Yuancheng Xu, Chenghao Deng, Yanchao Sun, Ruijie Zheng, Xiyao Wang, Jieyu Zhao, Furong Huang

Comments Published at the Forty-first International Conference on Machine Learning (ICML 2024)

Graph Automorphism Group Equivariant Neural Networks

Edward Pearce-Crump, William J. Knottenbelt

Comments ICML 2024 Poster; 27 pages

Naive Bayes Classifiers over Missing Data: Decision and Poisoning

Song Bian, Xiating Ouyang, Zhiwei Fan, Paraschos Koutris

Comments 22 pages, 10 figures

Journal ref ICML 2024

Best Arm Identification for Stochastic Rising Bandits

Marco Mussi, Alessandro Montenegro, Francesco Trovó, Marcello Restelli, Alberto Maria Metelli

Comments Accepted to ICML 2024

Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts

Ha Manh Bui, Anqi Liu

Comments International Conference on Machine Learning, 2024

On the importance of cross-task features for class-incremental learning

Albin Soutif--Cormerais, Marc Masana, Joost van de Weijer, Bartłomiej Twardowski

Comments Accepted at the Theory and Foundation of Continual Learning Workshop, International Conference on Machine Learning (ICML) 2021. Supplementary material included. V4 includes additional results of linear probing of intermediate representations that were added to the supplementary

From Neurons to Neutrons: A Case Study in Interpretability

Ouail Kitouni, Niklas Nolte, Víctor Samuel Pérez-Díaz, Sokratis Trifinopoulos, Mike Williams

Comments International Conference on Machine Learning (ICML) 2024

Autoformalizing Euclidean Geometry

Logan Murphy, Kaiyu Yang, Jialiang Sun, Zhaoyu Li, Anima Anandkumar, Xujie Si

Comments Accepted to ICML 2024. The first two authors contributed equally

Q-value Regularized Transformer for Offline Reinforcement Learning

Shengchao Hu, Ziqing Fan, Chaoqin Huang, Li Shen, Ya Zhang, Yanfeng Wang, Dacheng Tao

Comments Published at ICML 2024

Recurrent Early Exits for Federated Learning with Heterogeneous Clients

Royson Lee, Javier Fernandez-Marques, Shell Xu Hu, Da Li, Stefanos Laskaridis, Łukasz Dudziak, Timothy Hospedales, Ferenc Huszár, Nicholas D. Lane

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

Language-guided Skill Learning with Temporal Variational Inference

Haotian Fu, Pratyusha Sharma, Elias Stengel-Eskin, George Konidaris, Nicolas Le Roux, Marc-Alexandre Côté, Xingdi Yuan

Comments ICML 2024

Accelerating Parallel Sampling of Diffusion Models

Zhiwei Tang, Jiasheng Tang, Hao Luo, Fan Wang, Tsung-Hui Chang

Comments ICML 2024

Unsupervised Evaluation of Code LLMs with Round-Trip Correctness

Miltiadis Allamanis, Sheena Panthaplackel, Pengcheng Yin

Comments Published in ICML 2024

Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes

Zhen Qin, Daoyuan Chen, Bingchen Qian, Bolin Ding, Yaliang Li, Shuiguang Deng

Comments Accepted to ICML 2024. 25 pages, 14 figures, 7 tables. Codes are available at https://github.com/alibaba/FederatedScope/tree/FedKSeed

HexGen: Generative Inference of Large Language Model over Heterogeneous Environment

Youhe Jiang, Ran Yan, Xiaozhe Yao, Yang Zhou, Beidi Chen, Binhang Yuan

Comments Accepted by ICML 2024

Federated Neuro-Symbolic Learning

Pengwei Xing, Songtao Lu, Han Yu

Comments accepted by ICML 2024

Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning

Mingqing Xiao, Yixin Zhu, Di He, Zhouchen Lin

Comments Accepted by ICML 2024

Transport of Algebraic Structure to Latent Embeddings

Samuel Pfrommer, Brendon G. Anderson, Somayeh Sojoudi

Comments Proceedings of the 41st International Conference on Machine Learning (2024)

Masked Face Recognition with Generative-to-Discriminative Representations

Shiming Ge, Weijia Guo, Chenyu Li, Junzheng Zhang, Yong Li, Dan Zeng

Comments Accepted by International Conference on Machine Learning 2024

Efficient Probabilistic Modeling of Crystallization at Mesoscopic Scale

Pol Timmer, Koen Minartz, Vlado Menkovski

Comments Under review in AI for Science @ ICML 2024

Reflected Flow Matching

Tianyu Xie, Yu Zhu, Longlin Yu, Tong Yang, Ziheng Cheng, Shiyue Zhang, Xiangyu Zhang, Cheng Zhang

Comments ICML 2024 camera-ready

SuDA: Support-based Domain Adaptation for Sim2Real Motion Capture with Flexible Sensors

Jiawei Fang, Haishan Song, Chengxu Zuo, Xiaoxia Gao, Xiaowei Chen, Shihui Guo, Yipeng Qin

Comments 20 pages conference, accepted ICML paper

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs

Kaituo Feng, Changsheng Li, Xiaolu Zhang, Jun Zhou, Ye Yuan, Guoren Wang

Comments Accepted by ICML 2024

Constrained Ensemble Exploration for Unsupervised Skill Discovery

Chenjia Bai, Rushuai Yang, Qiaosheng Zhang, Kang Xu, Yi Chen, Ting Xiao, Xuelong Li

Comments Accepted by ICML 2024

Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares

Liangzu Peng, Wotao Yin

Comments 36 pages, accepted to ICML 2024

Rethinking Independent Cross-Entropy Loss For Graph-Structured Data

Rui Miao, Kaixiong Zhou, Yili Wang, Ninghao Liu, Ying Wang, Xin Wang

Comments 20 pages, 4 figures

Journal ref ICML 2024

On the Tractability of SHAP Explanations under Markovian Distributions

Reda Marzouk, Colin de La Higuera

Comments Accepted at ICML 2024

Position: Why We Must Rethink Empirical Research in Machine Learning

Moritz Herrmann, F. Julian D. Lange, Katharina Eggensperger, Giuseppe Casalicchio, Marcel Wever, Matthias Feurer, David Rügamer, Eyke Hüllermeier, Anne-Laure Boulesteix, Bernd Bischl

Comments 20 pages, accepted for publication at ICML 2024, camera-ready version

Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning

Kyle Hsu, Jubayer Ibn Hamid, Kaylee Burns, Chelsea Finn, Jiajun Wu

Comments ICML 2024 camera-ready. 22 pages, 10 figures, code available at https://github.com/kylehkhsu/tripod