When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation Paper • 2608.03632 • Published 3 days ago • 18
When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition Paper • 2603.16256 • Published Mar 17 • 2
DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model Paper • 2512.12633 • Published Dec 14, 2025 • 2
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published Apr 6 • 236
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models Paper • 2512.24618 • Published Dec 31, 2025 • 155
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization Paper • 2512.24615 • Published Dec 31, 2025 • 119