Yong Yu

Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots

CATArena: Evaluation of LLM Agents Through Iterative Tournament Competitions

InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation

CoreCodeBench: A Configurable Multi-Scenario Repository-Level Benchmark

ATGen: Adversarial Reinforcement Learning for Test Case Generation

Unified Latent Steering and Residual Refinement for Online Improvement of Diffusion Policy Models

LoopTool: Closing the Data–Training Loop for Robust LLM Tool Calls

Improve LLM Pre-training with RL-Guided Annealing

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning

APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training

TRACEBench: Personalized Function Calling Benchmark Based on Real-World Human Interaction

DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning

Large Language Models are Demonstration Pre-Selectors for Themselves

Large Language Models are Demonstration Pre-Selectors for Themselves

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation