ICML

Population-level Dark Energy Constraints from Strong Gravitational Lensing using Simulation-Based Inference

Sreevani Jarugula, Brian Nord, Abhijith Gandrakota, Aleksandra Ćiprijanović

Comments Accepted to the workshop on AI for Science at the 41st International Conference on Machine Learning 2024 (ICML 2024)

Spectrum-Informed Multistage Neural Networks: Multiscale Function Approximators of Machine Precision

Jakin Ng, Yongji Wang, Ching-Yao Lai

Comments 8 pages, 3 figures, ICML 2024 workshop (AI for Science: Scaling in AI for Scientific Discovery)

Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis

Xiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre

Comments Accepted by ICML 2024 Next Generation of Sequence Modeling Architectures Workshop. Short version of arXiv:2406.16450

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

Eduard Gorbunov, Abdurakhmon Sadiev, Marina Danilova, Samuel Horváth, Gauthier Gidel, Pavel Dvurechensky, Alexander Gasnikov, Peter Richtárik

Comments ICML 2024; changes in version 2: minor corrections (typos were fixed and the structure was modified)

Generation Constraint Scaling Can Mitigate Hallucination

Georgios Kollias, Payel Das, Subhajit Chaudhury

Comments 7 pages; accepted at ICML 2024 Workshop on Large Language Models and Cognition

Variable Star Light Curves in Koopman Space

Nicolas Mekhaël, Mario Pasquato, Gaia Carenini, Vittorio F. Braga, Piero Trevisan, Giuseppe Bono, Yashar Hezaveh

Comments Accepted (spotlight) at the Scaling AI for Science workshop at ICML 2024

Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters

Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi, Viswanath Ganapathy, Rafael Esteves, Shreya Kadambi, Shubhankar Borse, Paul Whatmough, Risheek Garrepalli, Mart Van Baalen, Harris Teague, Markus Nagel

Comments Published at ICML 2024 Workshop on Foundation Models in the Wild. arXiv admin note: substantial text overlap with arXiv:2406.13175

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

Comments ICML'24 Spotlight

Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions

Kaihong Zhang, Caitlyn H. Yin, Feng Liang, Jingbo Liu

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60134-60178, 2024

Boosting Gradient Ascent for Continuous DR-submodular Maximization

Qixin Zhang, Zongqi Wan, Zengde Deng, Zaiyi Chen, Xiaoming Sun, Jialin Zhang, Yu Yang

Comments 74 pages, 6 figures and 9 tables. An extended version of Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function (ICML 2022)

COALA: A Practical and Vision-Centric Federated Learning Platform

Weiming Zhuang, Jian Xu, Chen Chen, Jingtao Li, Lingjuan Lyu

Comments ICML'24

PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing

Blazej Manczak, Eliott Zemour, Eric Lin, Vaikkunth Mugunthan

Comments ICML 2024 NextGenAISafety workshop version with links to implementation and dataset

Automatic Environment Shaping is the Next Frontier in RL

Younghyo Park, Gabriel B. Margolis, Pulkit Agrawal

Comments ICML 2024 Position Track; Website at https://auto-env-shaping.github.io/

LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies

Jia Shi, Gautam Gare, Jinjin Tian, Siqi Chai, Zhiqiu Lin, Arun Vasudevan, Di Feng, Francesco Ferroni, Shu Kong

Comments ICML 2024 Oral Presentation; Project Page: https://elvishelvis.github.io/papers/lca/

Accounting for Selection Effects in Supernova Cosmology with Simulation-Based Inference and Hierarchical Bayesian Modelling

Benjamin M. Boyd, Matthew Grayling, Stephen Thorp, Kaisey S. Mandel

Comments Accepted for the ICML AI for Science Workshop (2024). 13 pages, 5 figures, 2 tables

Large Language Models Lack Understanding of Character Composition of Words

Andrew Shin, Kunitake Kaneko

Comments ICML 2024 Workshop on Large Language Models and Cognition

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Piotr Nawrot, Adrian Łańcucki, Marcin Chochowski, David Tarjan, Edoardo M. Ponti

Journal ref Proceedings of the 41st International Conference on Machine Learning (2024) 37396-37412

Smooth Tchebycheff Scalarization for Multi-Objective Optimization

Xi Lin, Xiaoyuan Zhang, Zhiyuan Yang, Fei Liu, Zhenkun Wang, Qingfu Zhang

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

Position: AI/ML Influencers Have a Place in the Academic Process

Iain Xie Weissburg, Mehir Arora, Xinyi Wang, Liangming Pan, William Yang Wang

Comments 15 Pages, 22 Figures, ICML 2024

AI Control: Improving Safety Despite Intentional Subversion

Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, Fabien Roger

Comments Edit: Fix minor typos, clarify abstract, add glossary, expand related work. ICML version: https://openreview.net/pdf?id=KviM5k8pcP

Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC

Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani

Comments A long version of the ICML 2024 paper, updated the text about a related work

Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference

Marvin Schmitt, Desi R. Ivanova, Daniel Habermann, Ullrich Köthe, Paul-Christian Bürkner, Stefan T. Radev

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

Journal ref ICML 2024: PMLR 235, 2024

Estimating Probability Densities with Transformer and Denoising Diffusion

Henry W. Leung, Jo Bovy, Joshua S. Speagle

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

A New Theoretical Perspective on Data Heterogeneity in Federated Optimization

Jiayi Wang, Shiqiang Wang, Rong-Rong Chen, Mingyue Ji

Comments ICML 2024

Strongly Isomorphic Neural Optimal Transport Across Incomparable Spaces

Athina Sotiropoulou, David Alvarez-Melis

Comments ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling

Evaluation of RAG Metrics for Question Answering in the Telecom Domain

Sujoy Roychowdhury, Sumit Soman, H G Ranjani, Neeraj Gunda, Vansh Chhabra, Sai Krishna Bala

Comments Accepted for publication in ICML 2024 Workshop on Foundation Models in the Wild

Data Generation Using Large Language Models for Text Classification: An Empirical Case Study

Yinheng Li, Rogerio Bonatti, Sara Abdali, Justin Wagle, Kazuhito Koishida

Comments Accepted by DMLR @ ICML 2024

Towards diffusion models for large-scale sea-ice modelling

Tobias Sebastian Finn, Charlotte Durand, Alban Farchi, Marc Bocquet, Julien Brajard

Comments 21 pages, 5 Figures, Camera-ready version for the ICML 2024 Machine Learning for Earth System Modeling workshop

What is Dataset Distillation Learning?

William Yang, Ye Zhu, Zhiwei Deng, Olga Russakovsky

Comments ICML 2024

PANDA: Expanded Width-Aware Message Passing Beyond Rewiring

Jeongwhan Choi, Sumin Park, Hyowon Wi, Sung-Bae Cho, Noseong Park

Comments Accepted at ICML 2024