Yongqiang Chen

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

On the Thinking-Language Modeling Gap in Large Language Models

TRACEDET: HALLUCINATION DETECTION FROM THE DECODING TRACE OF DIFFUSION LARGE LANGUAGE MODELS

Concept Concentration for Faithful Representation Intervention

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

ParamAgent: Language Agents with Parametric Knowledge

LeGIT: LLM Guided Intervention Targeting for Online Causal Discovery

Learning Task-Sufficient World Models via Intervention-Curriculum Co-Design

Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization

Pruning Spurious Subgraphs for Graph Out-of-Distribtuion Generalization

Learning Graph Invariance by Harnessing Spuriosity

Hierarchical Graph Tokenization for Molecule-Language Alignment

Diversifying Spurious Subgraphs for Graph Out-of-Distribution Generalization

BrainOOD: Out-of-distribution Generalizable Brain Network Analysis

On the Language of Thoughts in Large Language Models

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation

Improving Molecule-Language Alignment with Hierarchical Graph Tokenization

Text Boosts Generalization: A Plug-and-Play Captioner for Real-World Image Restoration

Can Large Language Models Help Experimental Design for Causal Discovery?