ICML

Can Implicit Bias Imply Adversarial Robustness?

Hancheng Min, René Vidal

Comments icml 2024 camera-ready

Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)

Drew Prinster, Samuel Stanton, Anqi Liu, Suchi Saria

Comments ICML 2024. Code available at https://github.com/drewprinster/conformal-mfcs

Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?

M. Saquib Sarfraz, Mei-Yen Chen, Lukas Layer, Kunyu Peng, Marios Koulakis

Comments ICML 2024

CKGConv: General Graph Convolution with Continuous Kernels

Liheng Ma, Soumyasundar Pal, Yitian Zhang, Jiaming Zhou, Yingxue Zhang, Mark Coates

Comments On International Conference on Machine Learning (ICML) 2024

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation

Lujie Yang, Hongkai Dai, Zhouxing Shi, Cho-Jui Hsieh, Russ Tedrake, Huan Zhang

Comments Paper accepted by ICML 2024

Linguistic Calibration of Long-Form Generations

Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto

Comments ICML 2024. Code available at https://github.com/tatsu-lab/linguistic_calibration

Self-Supervised Interpretable End-to-End Learning via Latent Functional Modularity

Hyunki Seong, David Hyunchul Shim

Comments 12 pages, 9 figures. Accepted at ICML 2024. Camera-ready version

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction

He Zhang, Chang Liu, Zun Wang, Xinran Wei, Siyuan Liu, Nanning Zheng, Bin Shao, Tie-Yan Liu

Comments Accepted by ICML 2024

Convergence of Some Convex Message Passing Algorithms to a Fixed Point

Vaclav Voracek, Tomas Werner

Comments ICML 2024; comments are welcome

Scalable Online Exploration via Coverability

Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy

Comments ICML 2024

Controllable Prompt Tuning For Balancing Group Distributional Robustness

Hoang Phan, Andrew Gordon Wilson, Qi Lei

Comments Proceedings of the 41st International Conference on Machine Learning

Pairwise Alignment Improves Graph Domain Adaptation

Shikun Liu, Deyu Zou, Han Zhao, Pan Li

Comments ICML 2024. Our code and data are available at: https://github.com/Graph-COM/Pair-Align

Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding

Guangyi Liu, Yu Wang, Zeyu Feng, Qiyu Wu, Liping Tang, Yuan Gao, Zhen Li, Shuguang Cui, Julian McAuley, Zichao Yang, Eric P. Xing, Zhiting Hu

Comments ICML 2024 camera-ready. Code is available at https://github.com/guangyliu/EDDPM

On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Yihao Zhang, Hangzhou He, Jingyu Zhu, Huanran Chen, Yifei Wang, Zeming Wei

Comments ICML 2024

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein

Comments ICML 2024 Oral

Copyright Traps for Large Language Models

Matthieu Meeus, Igor Shilov, Manuel Faysse, Yves-Alexandre de Montjoye

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

How do Transformers perform In-Context Autoregressive Learning?

Michael E. Sander, Raja Giryes, Taiji Suzuki, Mathieu Blondel, Gabriel Peyré

Comments 20 pages ICML 2024

Towards Efficient Exact Optimization of Language Model Alignment

Haozhe Ji, Cheng Lu, Yilin Niu, Pei Ke, Hongning Wang, Jun Zhu, Jie Tang, Minlie Huang

Comments 24 pages, 9 figures

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

Efficient Exploration for LLMs

Vikranth Dwaracherla, Seyed Mohammad Asghari, Botao Hao, Benjamin Van Roy

Comments Accepted at ICML 2024

Sampling in Unit Time with Kernel Fisher-Rao Flow

Aimee Maurais, Youssef Marzouk

Comments To appear at ICML 2024. Updated with additional numerical examples

An LLM Compiler for Parallel Function Calling

Sehoon Kim, Suhong Moon, Ryan Tabrizi, Nicholas Lee, Michael W. Mahoney, Kurt Keutzer, Amir Gholami

Comments ICML 2024

Interpretability Illusions in the Generalization of Simplified Models

Dan Friedman, Andrew Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun

Comments ICML 2024

Recurrent Distance Filtering for Graph Representation Learning

Yuhui Ding, Antonio Orvieto, Bobby He, Thomas Hofmann

Comments ICML 2024

StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization

Shida Wang, Qianxiao Li

Comments 28 pages, 7 figures, ICML 2024

Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments

Allen Tran, Aurélien Bibaut, Nathan Kallus

Comments Accepted into ICML 2024 - typos etc and extended literature review

Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction

Arjun Subramonian, Levent Sagun, Yizhou Sun

Comments Accepted to ICML 2024

Rethinking Momentum Knowledge Distillation in Online Continual Learning

Nicolas Michel, Maorong Wang, Ling Xiao, Toshihiko Yamasaki

Comments Accepted to ICML 2024

Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues

Antonio Orvieto, Soham De, Caglar Gulcehre, Razvan Pascanu, Samuel L. Smith

Comments v1: Accepted at HLD 2023 Workshop @ICML; v2: Preprint; v3: ICML version

SqueezeLLM: Dense-and-Sparse Quantization

Sehoon Kim, Coleman Hooper, Amir Gholami, Zhen Dong, Xiuyu Li, Sheng Shen, Michael W. Mahoney, Kurt Keutzer

Comments ICML 2024

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

Runze Liu, Yali Du, Fengshuo Bai, Jiafei Lyu, Xiu Li

Comments Accepted to ICML 2024