ICML 2024 Conference Submissions

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
Justin Chen, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
Zixuan Wang, Stanley Wei, Daniel Hsu, Jason D. Lee
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
On the Consistency of Kernel Methods with Dependent Observations
Pierre-François Massiani, Sebastian Trimpe, Friedrich Solowjow
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Self-Rewarding Language Models
Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, Jason E Weston
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
Daniel D. Johnson, Daniel Tarlow, David Duvenaud, Chris J. Maddison
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective
Yulong Zhang, Yuan Yao, Shuhao Chen, Pengrong Jin, Yu Zhang, Jian Jin, Jiangang Lu
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
Yueqi XIE, Minghong Fang, Neil Zhenqiang Gong
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Dynamic Metric Embedding into lp Space
Kiarash Banihashem, MohammadTaghi Hajiaghayi, Dariusz Rafal Kowalski, Jan Olkowski, Max Springer
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance
Liwen Sun, Abhineet Agarwal, Aaron Kornblith, Bin Yu, Chenyan Xiong
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Trainable Transformer in Transformer
Abhishek Panigrahi, Sadhika Malladi, Mengzhou Xia, Sanjeev Arora
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
Fuzhong Zhou, Chenyu Zhang, Xu Chen, Xuan Di
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Performative Prediction with Bandit Feedback: Learning through Reparameterization
Yatong Chen, Wei Tang, Chien-Ju Ho, Yang Liu
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Probabilistic Modeling of Interpersonal Coordination Processes
Paulo Soares, Adarsh Pyarelal, Meghavarshini Krishnaswamy, Emily Butler, Kobus Barnard
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Statistical Properties of Robust Satisficing
zhiyi li, Yunbei Xu, Ruohan Zhan
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability
Sepanta Zeighami, Cyrus Shahabi
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Oral
- Readers: Everyone
Recurrent Early Exits for Federated Learning with Heterogeneous Clients
Royson Lee, Javier Fernandez-Marques, Shell Xu Hu, Da Li, Stefanos Laskaridis, Łukasz Dudziak, Timothy Hospedales, Ferenc Huszár, Nicholas Donald Lane
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
MALIBO: Meta-learning for Likelihood-free Bayesian Optimization
Jiarong Pan, Stefan Falkner, Felix Berkenkamp, Joaquin Vanschoren
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Spotlight
- Readers: Everyone
A decoder-only foundation model for time-series forecasting
Abhimanyu Das, Weihao Kong, Rajat Sen, Yichen Zhou
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Learning High-Order Relationships of Brain Regions
Weikang Qiu, Huangrui Chu, Selena Wang, Haolan Zuo, Xiaoxiao Li, Yize Zhao, Rex Ying
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order Oracles
Phillip Kerger, Marco Molinaro, Hongyi Jiang, Amitabh Basu
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms
Yuchen Li, Laura Balzano, Deanna Needell, Hanbaek Lyu
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Understanding Stochastic Natural Gradient Variational Inference
Kaiwen Wu, Jacob R. Gardner
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Position: A Safe Harbor for AI Evaluation and Red Teaming
Shayne Longpre, Sayash Kapoor, Kevin Klyman, Ashwin Ramaswami, Rishi Bommasani, Borhane Blili-Hamelin, Yangsibo Huang, Aviya Skowron, Zheng Xin Yong, Suhas Kotha, Yi Zeng, Weiyan Shi, Xianjun Yang, Reid Southen, Alexander Robey, Patrick Chao, Diyi Yang, Ruoxi Jia, Daniel Kang, Alex Pentland et al. (3 additional authors not shown)
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Oral
- Readers: Everyone
FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data
Shusen Jing, Anlan Yu, Shuai Zhang, Songyang Zhang
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone
Biharmonic Distance of Graphs and its Higher-Order Variants: Theoretical Properties with Applications to Centrality and Clustering
Mitchell Black, Lucy Lin, Weng-Keen Wong, Amir Nayyeri
- Published: 02 May 2024, Last Modified: 25 Jun 2024
- ICML 2024 Poster
- Readers: Everyone