Guanhua Chen

Assistant Professor@Southern University of Science and Technology·中国·OpenReview

研究方向

large language model · data synthesis · llm-as-a-judge · multimodal LLMs · reasoning LLMs · reinforcement learning · neural machine translation · multilingual NMT · cross-lingual transfer

Guanhua Chen

Fair Decision Utility in Human-AI Collaboration: Interpretable Confidence Adjustment for Humans with Cognitive Disparities

InfoScan: Information-Efficient Visual Scanning via Resource-Adaptive Walks

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics

Tree Search for LLM Agent Reinforcement Learning

Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning

Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning

BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation

Anchored Supervised Fine-Tuning

AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection

CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling

Automatic Robustness Stress Testing of LLMs as Mathematical Problem Solvers

Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization

Benchmarking Long-Term Memory with Continuous dialogue Lifelogs

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks

Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection

Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations