James Cheng

Reducing Belief Deviation in Reinforcement Learning for Active Reasoning of LLM Agents

On the Thinking-Language Modeling Gap in Large Language Models

Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection

On the Measurement and Efficient Mitigation of Length Generalization Gaps in Large Language Models

A Signed Graph Approach to Understanding and Mitigating Oversmoothing

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models

Hierarchical Graph Tokenization for Molecule-Language Alignment

BrainOOD: Out-of-distribution Generalizable Brain Network Analysis

Oversmoothing as Loss of Sign: Towards Structural Balance in Graph Neural Networks

On the Language of Thoughts in Large Language Models

Improving Molecule-Language Alignment with Hierarchical Graph Tokenization