ICML

AST-T5: Structure-Aware Pretraining for Code Generation and Understanding

Linyuan Gong, Mostafa Elhoushi, Alvin Cheung

Comments 15 pages; ICML 2024: https://icml.cc/virtual/2024/poster/33601

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts

Huy Nguyen, Pedram Akbarian, TrungTin Nguyen, Nhat Ho

Comments Accepted to ICML 2024, 32 pages, 3 figures, 3 tables

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low

Comments Accepted to ICML 2024

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

Ang Li, Yichuan Mo, Mingjie Li, Yisen Wang

Comments 27 pages, ICML 2024 poster

Using Neural Networks for Data Cleaning in Weather Datasets

Jack R. P. Hanslope, Laurence Aitchison

Comments 6 pages, 2 figures, ICML 2024 Workshop on Machine Learning for Earth System Modeling

Impact of Decentralized Learning on Player Utilities in Stackelberg Games

Kate Donahue, Nicole Immorlica, Meena Jagadeesan, Brendan Lucier, Aleksandrs Slivkins

Comments To appear at ICML 2024; this is the full version

Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error

Haoran Li, Zicheng Zhang, Wang Luo, Congying Han, Yudong Hu, Tiande Guo, Shichen Liao

Journal ref ICML 2024 Oral

Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization

Deokjae Lee, Hyun Oh Song, Kyunghyun Cho

Comments ICML 2024; Codes at https://github.com/snu-mllab/GreedyPolicyForMOCO

Understanding Finetuning for Factual Knowledge Extraction

Gaurav Ghosal, Tatsunori Hashimoto, Aditi Raghunathan

Comments To appear in ICML 2024

A General Online Algorithm for Optimizing Complex Performance Metrics

Wojciech Kotłowski, Marek Wydmuch, Erik Schultheis, Rohit Babbar, Krzysztof Dembczyński

Comments This is the authors' version of the work accepted to ICML 2024

Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

Yeonhong Park, Jake Hyun, SangLyul Cho, Bonggeun Sim, Jae W. Lee

Comments To appear at ICML 2024. Code is available at https://github.com/SNU-ARC/any-precision-llm

Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations

Helen Qu, Sang Michael Xie

Comments ICML 2024

Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation

Xinyi Wang, Alfonso Amayuelas, Kexun Zhang, Liangming Pan, Wenhu Chen, William Yang Wang

Comments Accepted to ICML 2024

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

Zhengqing Yuan, Zhaoxu Li, Weiran Huang, Yanfang Ye, Lichao Sun

Comments Accepted by ICML workshop 2024

One-Shot Strategic Classification Under Unknown Costs

Elan Rosenfeld, Nir Rosenfeld

Comments Accepted to ICML 2024

Revealing Vision-Language Integration in the Brain with Multimodal Networks

Vighnesh Subramaniam, Colin Conwell, Christopher Wang, Gabriel Kreiman, Boris Katz, Ignacio Cases, Andrei Barbu

Comments ICML 2024; 23 pages, 11 figures

Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations

Niklas Freymuth, Philipp Dahlinger, Tobias Würth, Philipp Becker, Aleksandar Taranovic, Onno Grönheim, Luise Kärger, Gerhard Neumann

Comments Accepted as a workshop paper in AI4Science@ICML 2024

Allocation Requires Prediction Only if Inequality Is Low

Ali Shirali, Rediet Abebe, Moritz Hardt

Comments Appeared in Forty-first International Conference on Machine Learning (ICML), 2024

Text Serialization and Their Relationship with the Conventional Paradigms of Tabular Machine Learning

Kyoka Ono, Simon A. Lee

Comments Accepted into the ICML AI4Science Workshop

Improving GFlowNets with Monte Carlo Tree Search

Nikita Morozov, Daniil Tiapkin, Sergey Samsonov, Alexey Naumov, Dmitry Vetrov

Comments ICML 2024 SPIGM Workshop

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

Dachun Kai, Jiayao Lu, Yueyi Zhang, Xiaoyan Sun

Comments ICML 2024. Project page: https://dachunkai.github.io/evtexture.github.io/

Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem

Zhentao Tan, Yadong Mu

Comments Accepted by ICML 2024

Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention

Zhen Qin, Weigao Sun, Dong Li, Xuyang Shen, Weixuan Sun, Yiran Zhong

Comments Accepted by ICML 2024. Yiran Zhong is the corresponding author. Code is released at github.com/OpenNLPLab/TransnormerLLM

Progress Measures for Grokking on Real-world Tasks

Satvik Golechha

Comments 5 pages

Journal ref ICML 2024 Workshop on High-dimensional Learning Dynamics (HiLD)

Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized

Shomik Jain, Kathleen Creel, Ashia Wilson

Comments To appear in the proceedings of the International Conference on Machine Learning (ICML 2024)

HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption

Seewoo Lee, Garam Lee, Jung Woo Kim, Junbum Shin, Mun-Kyu Lee

Comments ICML 2023, Appendix D includes some updates after official publication

Journal ref PMLR 202:19010-19035, 2023

Listenable Maps for Audio Classifiers

Francesco Paissan, Mirco Ravanelli, Cem Subakan

Comments Accepted to ICML 2024 (Oral)

EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning

Jongsuk Kim, Hyeongkeun Lee, Kyeongha Rho, Junmo Kim, Joon Son Chung

Comments 15 pages, 3 figures; Accepted to ICML 2024 (camera ready version)

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

Michal Nauman, Michał Bortkiewicz, Piotr Miłoś, Tomasz Trzciński, Mateusz Ostaszewski, Marek Cygan

Comments ICML 2024

Prospector Heads: Generalized Feature Attribution for Large Models & Data

Gautam Machiraju, Alexander Derry, Arjun Desai, Neel Guha, Amir-Hossein Karimi, James Zou, Russ Altman, Christopher Ré, Parag Mallick

Comments 30 pages, 16 figures, 8 tables. Accepted to ICML 2024