[Apr. 2026] 🔥 Hy3-preview is open-sourced! Honored to contribute to the RL post-training. Welcome to try and follow our work at Tencent Hy Research.
Research
My current research focuses on Multimodal Large Language Models (MLLMs), specifically revolutionizing reinforcement learning for the alignment of Vision-Language Models and continuously pushing the boundaries of their reasoning ability to unlock full potential in complex scenarios.