ICML

Two Tales of Single-Phase Contrastive Hebbian Learning

Rasmus Kjær Høier, Christopher Zach

Comments ICML 2024; 21 pages

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, Lijuan Wang

Comments ICML 2024. Code, data and leaderboard: https://github.com/yuweihao/MM-Vet

Causal Inference in Finance: An Expertise-Driven Model for Instrument Variables Identification and Interpretation

Ying Chen, Ziwei Xu, Kotaro Inoue, Ryutaro Ichise

Comments 23rd International Conference on Machine Learning and Applications (ICMLA)

UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation

Junhong Shen, Tanya Marwah, Ameet Talwalkar

Comments TMLR 2024; ICML 2024 AI for Science Workshop (Spotlight)

Sample Complexity of Probability Divergences under Group Symmetry

Ziyu Chen, Markos A. Katsoulakis, Luc Rey-Bellet, Wei Zhu

Comments In addition to our published version at ICML 2023, we include the case when the group is infinite such as compact Lie groups. Our approach is different from that in [Tahmasebi & Jegelka, ICML 2024] and our work also applies to asymmetric divergences, such as the Lipschitz-regularized $α$-divergences

Financial Fraud Detection using Jump-Attentive Graph Neural Networks

Prashank Kadam

Comments International Conference on Machine Learning and Applications 2024

A Review of Electromagnetic Elimination Methods for low-field portable MRI scanner

Wanyu Bian, Panfeng Li, Mengyao Zheng, Chihang Wang, Anying Li, Ying Li, Haowei Ni, Zixuan Zeng

Comments Accepted by 2024 5th International Conference on Machine Learning and Computer Application

Journal ref Proceedings of the 2024 5th International Conference on Machine Learning and Computer Application (ICMLCA), 2024, pp. 614-618

Simulation-Based Inference with Quantile Regression

He Jia

Comments 9+13 pages, 8+8 figures, ICML 2024

Exploring the Low-Pass Filtering Behavior in Image Super-Resolution

Haoyu Deng, Zijing Xu, Yule Duan, Xiao Wu, Wenjie Shu, Liang-Jian Deng

Comments Accepted by ICML 2024

Generalization on the Unseen, Logic Reasoning and Degree Curriculum

Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Kevin Rizk

Comments extended JMLR version of the original ICML 2023 paper

SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models

Zhaoxu Luo, Bowen Song, Liyue Shen

Comments Accepted by ICML 2024 Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization

KTO: Model Alignment as Prospect Theoretic Optimization

Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, Douwe Kiela

Comments ICML 2024

Contextual Combinatorial Bandits with Probabilistically Triggered Arms

Xutong Liu, Jinhang Zuo, Siwei Wang, John C. S. Lui, Mohammad Hajiesmaili, Adam Wierman, Wei Chen

Comments The 40th International Conference on Machine Learning (ICML), 2023

Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT

Jon Saad-Falcon, Daniel Y. Fu, Simran Arora, Neel Guha, Christopher Ré

Comments International Conference on Machine Learning (ICML) 2024

Sample as You Infer: Predictive Coding With Langevin Dynamics

Umais Zahid, Qinghai Guo, Zafeirios Fountas

Comments FID values updated to use a fixed 50,000 samples for all experiments - Jeffrey's divergence now consistently best performing. Dynov2 based metrics removed due to inconsistency of results - and since not industry standard. Multiple beta values tested in Fig 4. Theta LR for VAEs; beta and inf LR for LPC now tuned for results. Figure 5B updated; curves now correspond to results in Table 1

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58105-58121, 2024

Smooth Non-Stationary Bandits

Su Jia, Qian Xie, Nathan Kallus, Peter I. Frazier

Comments Accepted by ICML 2023

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, Xinggang Wang

Comments Vision Mamba (Vim) is accepted by ICML 2024. Code is available at https://github.com/hustvl/Vim

Machine Learning Global Simulation of Nonlocal Gravity Wave Propagation

Aman Gupta, Aditi Sheshadri, Sujit Roy, Vishal Gaur, Manil Maskey, Rahul Ramachandran

Comments International Conference on Machine Learning 2024

Inferring Graphs from Cascades: A Sparse Recovery Framework

Jean Pouget-Abadie, Thibaut Horel

Comments Full version of the ICML paper with the same title

Journal ref Proceedings of the 32nd International Conference on Machine Learning, 2015, pp. 977-986

A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation

Qikai Yang, Panfeng Li, Xinhe Xu, Zhicheng Ding, Wenjing Zhou, Yi Nian

Comments Accepted by 2024 4th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)

Journal ref Proceedings of the 2024 4th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), 2024, pp. 214-218

Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability

Sepanta Zeighami, Cyrus Shahahbi

Comments Appeared in ICML'24 (oral)

Sensitivity of MCMC-based analyses to small-data removal

Tin D. Nguyen, Ryan Giordano, Rachael Meager, Tamara Broderick

Comments Shorter version appeared in ICML 2024 Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators

Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models

Dennis Wu, Jerry Yao-Chieh Hu, Teng-Yun Hsiao, Han Liu

Comments Accepted at ICML 2024; v3 added a note on follow-up UHop+ (arXiv:2410.23126); v2 updated to camera-ready version; Code available at https://github.com/MAGICS-LAB/UHop

Equivariant Deep Weight Space Alignment

Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik, Nadav Dym, Haggai Maron

Comments ICML 2024

Enhancing Financial Fraud Detection with Human-in-the-Loop Feedback and Feedback Propagation

Prashank Kadam

Comments International Conference on Machine Learning and Applications 2024

Do Efficient Transformers Really Save Computation?

Kai Yang, Jan Ackermann, Zhenyu He, Guhao Feng, Bohang Zhang, Yunzhen Feng, Qiwei Ye, Di He, Liwei Wang

Comments 20 pages, ICML 2024 Camera Ready Version

Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification

Thomas Kwa, Drake Thomas, Adrià Garriga-Alonso

Comments Mechanistic Interpretability workshop at ICML 2024; Main conference poster at NeurIPS 2024

Exploring the LLM Journey from Cognition to Expression with Linear Representations

Yuzi Yan, Jialian Li, Yipin Zhang, Dong Yan

Comments Published in ICML 2024

Initial Guessing Bias: How Untrained Networks Favor Some Classes

Emanuele Francazi, Aurelien Lucchi, Marco Baity-Jesi

Comments Fixed notation typos in Figure3 and Figure4

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13783-13839, 2024

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data

Nikita Tsoy, Nikola Konstantinov

Comments ICML 2024, camera-ready version (expanded related work)