Xinyu Dai

TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them

Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards

GePBench: Evaluating Fundamental Geometric Perception for Multimodal Large Language Models

AutoSurvey: Large Language Models Can Automatically Write Surveys

Dynamic Demonstrations Controller for In-Context Learning

Multi-Scale Protein Language Model for Unified Molecular Modeling