4 papers
Cooperative Multi-agent RL with Communication Constraints
Nuoya Xiong, Aarti Singh
Cooperative MARL often assumes frequent access to global information in a data buffer, such as team rewards or other agents' actions, which is typically unrealistic in decentralize…
Token-Level LLM Collaboration via FusionRoute
Nuoya Xiong, Yuhang Zhou, Hanqing Zeng +5
Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a single general-purpose model typically requ…
Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
Nuoya Xiong, Aarti Singh
Reinforcement Learning with Human Feedback (RLHF) is a widely used fine-tuning approach that aligns machine learning model, particularly Language Model (LM) with human preferences.…
How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
Nuoya Xiong, Lijun Ding, Simon S. Du
This paper rigorously shows how over-parameterization changes the convergence behaviors of gradient descent (GD) for the matrix sensing problem, where the goal is to recover an unk…