ICML

Biharmonic Distance of Graphs and its Higher-Order Variants: Theoretical Properties with Applications to Centrality and Clustering

Mitchell Black, Lucy Lin, Amir Nayyeri, Weng-Keen Wong

Comments Accepted to ICML 2024. In v2, we correct an error in the definition of electrical flows and, accordingly, the proofs of Lemma 2.2 and Theorem 4.1

The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Kiho Park, Yo Joong Choe, Yibo Jiang, Victor Veitch

Comments Accepted for an oral presentation at ICLR 2025. Best Paper Award at the ICML 2024 Workshop on Mechanistic Interpretability. Code is available at https://github.com/KihoPark/LLM_Categorical_Hierarchical_Representations

GLAD: Improving Latent Graph Generative Modeling with Simple Quantization

Van Khoa Nguyen, Yoann Boget, Frantzeska Lavda, Alexandros Kalousis

Comments AAAI 2025 (Previously accepted at SPIGM ICML 2024 workshop)

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring

Taira Tsuchiya, Shinji Ito, Junya Honda

Comments Published version in Proceedings of 41st International Conference on Machine Learning (ICML 2024), 23 pages

Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations

Minung Kim, Kawon Lee, Jungmo Kim, Sungho Choi, Seungyul Han

Comments 8 pages main, 19 pages appendix with reference. Submitted to ICML 2025

Associative Recurrent Memory Transformer

Ivan Rodkin, Yuri Kuratov, Aydar Bulatov, Mikhail Burtsev

Comments ICML 2024 Next Generation of Sequence Modeling Architectures Workshop

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning

Saber Malekmohammadi, Yaoliang Yu, Yang Cao

Comments Proceedings of the 41 st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024

Learning a Diffusion Model Policy from Rewards via Q-Score Matching

Michael Psenka, Alejandro Escontrela, Pieter Abbeel, Yi Ma

Comments ICML 2024. 21 pages, 9 figures

Learning to Decouple Complex Systems

Zihan Zhou, Tianshu Yu

Journal ref Proceedings of the 40th International Conference on Machine Learning (ICML 2023), PMLR 202

Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding

Ghazal Kasalaee, Ali Hasanzadeh Karkan, Jean-François Frigon, François Leduc-Primeau

Comments This preprint comprises 6 pages and features 3 figures. It has been accepted to the IEEE International Conference on Machine Learning and Computer Networking (ICMLCN) 2025

A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites

Ali Hasanzadeh Karkan, Ahmed Ibrahim, Jean-François Frigon, François Leduc-Primeau

Comments This preprint comprises 6 pages and features 2 figures. It has been accepted to the IEEE International Conference on Machine Learning and Computer Networking (ICMLCN) 2025

Feature contamination: Neural networks learn uncorrelated features and fail to generalize

Tianren Zhang, Chujie Zhao, Guanyu Chen, Yizhou Jiang, Feng Chen

Comments ICML 2024

SAGE-HB: Swift Adaptation and Generalization in Massive MIMO Hybrid Beamforming

Ali Hasanzadeh Karkan, Hamed Hojatian, Jean-François Frigon, François Leduc-Primeau

Comments This preprint comprises 6 pages and features 5 figures. It has been accepted to the IEEE International Conference on Machine Learning and Computer Networking (ICMLCN) 2024

TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model

Defu Cao, Wen Ye, Yizhou Zhang, Yan Liu

Comments 31 Pages, 11 Figures, 22 Tables. First present at ICML 2024 Workshop on Foundation Models in the Wild

Diffeomorphic Temporal Alignment Nets for Time-series Joint Alignment and Averaging

Ron Shapira Weber, Oren Freifeld

Comments This manuscript covers and extends the papers: Diffeomorphic Temporal Alignment Nets (DTAN; NeruIPS 2019) and Regularization-free Diffeomorphic Temporal Alignment Nets (ICML 2023). Additional contributions: Multi-tasking DTAN, PCA-DTAN and more

Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise

Thomas Pouplin, Alan Jeffares, Nabeel Seedat, Mihaela van der Schaar

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

Constrained Efficient Global Optimization of Expensive Black-box Functions

Wenjie Xu, Yuning Jiang, Bratislav Svetozarevic, Colin N. Jones

Comments Accepted to ICML 2023; We revise the Theorem 5.1 on infeasibility declaration in the published version of PMLR

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Wei Chen, Zhen Huang, Liang Xie, Binbin Lin, Houqiang Li, Le Lu, Xinmei Tian, Deng Cai, Yonggang Zhang, Wenxiao Wang, Xu Shen, Jieping Ye

Comments accepted by ICML 2024, code and data are available at https://github.com/yellowtownhz/sycophancy-interpretability

AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios

Zhongzhan Huang, Mingfu Liang, Shanshan Zhong, Liang Lin

Comments Accepted by ICML'24

Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with Double Power-law Behavior

Fadhel Ayed, Juho Lee, François Caron

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:395-404, 2019

Adaptive Observation Cost Control for Variational Quantum Eigensolvers

Christopher J. Anders, Kim A. Nicoli, Bingting Wu, Naima Elosegui, Samuele Pedrielli, Lena Funcke, Karl Jansen, Stefan Kühn, Shinichi Nakajima

Comments 9 pages, 6 figures, 41st International Conference on Machine Learning (ICML 2024)

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks

Hojoon Lee, Hyeonseo Cho, Hyunseung Kim, Donghu Kim, Dugki Min, Jaegul Choo, Clare Lyle

Comments accepted to ICML 2024

RPGBENCH: Evaluating Large Language Models as Role-Playing Game Engines

Pengfei Yu, Dongming Shen, Silin Meng, Jaewon Lee, Weisu Yin, Andrea Yaoyun Cui, Zhenlin Xu, Yi Zhu, Xingjian Shi, Mu Li, Alex Smola

Comments Submitted to ICML 2025

Looking into the Future of Health-Care Services: Can Life-Like Agents Change the Future of Health-Care Services?

Mohammad Saleh Torkestani, Robert Davis, Abdolhossein Sarrafzadeh

Comments 6 pages, 2 figures, 3rd International Conference on Machine Learning and Computing (ICMLC 2011): February 26-28, 2011, Singapore

Journal ref 3rd International Conference on Machine Learning and Computing (ICMLC 2011): February 26-28, 2011, Singapore. ISBN: 978-1-4244-9252-7

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks

Amit Peleg, Matthias Hein

Comments Accepted at ICML 2024. Fixed a bug in Kaiming Gaussian initialization, does not affect the results of the paper

Restoring balance: principled under/oversampling of data for optimal classification

Emanuele Loffredo, Mauro Pastore, Simona Cocco, Rémi Monasson

Comments 9 pages + appendix, 3 figures. Presented at ICML'24

Journal ref Proceedings of the 41st International Conference on Machine Learning (ICML'24), PMLR 235:32643-32670, 2024

Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation

JoonHo Lee, Jae Oh Woo, Juree Seok, Parisa Hassanzadeh, Wooseok Jang, JuYoun Son, Sima Didari, Baruch Gutow, Heng Hao, Hankyu Moon, Wenjun Hu, Yeong-Dae Kwon, Taehee Lee, Seungjai Min

Comments Accepted to ICML 2024

On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows

Felix Draxler, Stefan Wahl, Christoph Schnörr, Ullrich Köthe

Comments Proceedings of the 41 st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024

Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors

Peter Lorenz, Mario Fernandez, Jens Müller, Ullrich Köthe

Comments accepted at ICML workshop 2024

Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization

Ruizhong Qiu, Hanghang Tong

Comments ICML 2024