Wenhao Yu

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Don't Throw Away Your Pretrained Model

Vision-SR1: Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking

On the Evolution of Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment

VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks