Strong Representation for ECE Faculty at ICML

news story image

The University of Maryland had a strong showing at the 40th International Conference on Machine Learning (ICML) 2023, held last month in Honolulu, Hawaii.  The Outstanding Paper Award was presented to UMD researchers John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, and Tom Goldstein (Katz and Goldstein are affiliated with ECE).  Their paper, titled “A Watermark for Large Language Models” focuses on embedding watermarks into large language models to help identify the source of specific outputs generated by the model.

Other papers presented by ECE faculty include:

Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation 

 Asuman Ozdaglar, Sarath Pattathil, Jiawei Zhang, Kaiqing Zhang (ECE)


STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning

 Souradip Chakraborty (UMD), Amrit Bedi (UMD), Alec Koppel, Mengdi Wang, Furong Huang (UMD), Dinesh Manocha (ECE)


Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees

 Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta (ECE)


Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic

 Wesley A. Suttle, Amrit Bedi (UMD), Bhrij Patel, Brian Sadler, Alec Koppel, Dinesh Manocha (ECE)


Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing 

Xiangyu Liu, Kaiqing Zhang (ECE)


Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction

Jianyi Zhang, Ang Li (ECE), Minxue Tang, Jingwei Sun, Xiang Chen, Fan Zhang, Changyou Chen, Yiran Chen · Hai Li





Published August 9, 2023