WideSearch: Benchmarking Agentic Broad Info-Seeking Paper • 2508.07999 • Published Aug 11, 2025 • 110
QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design Paper • 2505.16175 • Published May 22, 2025 • 42
Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning Paper • 2505.15966 • Published May 21, 2025 • 53
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values Paper • 2504.05535 • Published Apr 7, 2025 • 44
YuE: Scaling Open Foundation Models for Long-Form Music Generation Paper • 2503.08638 • Published Mar 11, 2025 • 71
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines Paper • 2502.14739 • Published Feb 20, 2025 • 106
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines Paper • 2502.14739 • Published Feb 20, 2025 • 106