2 citations · 7 across the 9 of their papers we have counts for
9 papers
Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
Hao Liang, Shuqing Shi, Yudi Zhang +2
Large-scale networked systems, such as traffic, power, and wireless grids, challenge reinforcement-learning agents with both scale and environment shifts. To address these challeng…
Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving
Shunfeng Zheng, Yudi Zhang, Meng Fang +4
Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning-such as solving Olym…
PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
Olivier Schipper, Yudi Zhang, Yali Du +2
LLM-based agents have shown promise in various cooperative and strategic reasoning tasks, but their effectiveness in competitive multi-agent environments remains underexplored. To…
Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?
Yudi Zhang, Lu Wang, Meng Fang +8
Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the pote…
RuAG: Learned-rule-augmented Generation for Large Language Models
Yudi Zhang, Pei Xiao, Lu Wang +11
In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer…
Large Language Models Are Neurosymbolic Reasoners
Meng Fang, Shilong Deng, Yudi Zhang +4
A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning. This paper investigates the potential a…
MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment
Ziyan Wang, Yali Du, Yudi Zhang +2
Offline Multi-agent Reinforcement Learning (MARL) is valuable in scenarios where online interaction is impractical or risky. While independent learning in MARL offers flexibility a…
Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
Yudi Zhang, Yali Du, Biwei Huang +4
A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution…
RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking
Fangwei Zhong, Xiao Bi, Yudi Zhang +2
Active Object Tracking (AOT) aims to maintain a specific relation between the tracker and object(s) by autonomously controlling the motion system of a tracker given observations. A…