💼 Experience

• March 2026 – Present · Qingyun Program Intern, Tencent Hunyuan
  Participating in the development of Hunyuan Hy3 and Hy4, with a focus on multimodal post-training, embodied perception, and long-horizon reasoning. I also contributed to Hy-Embodied-VLM-1.0, an MoE vision-language model that activates only 3B parameters.

• November 2024 – March 2026 · Research Intern, ByteDance (Volcano Engine Multimedia Laboratory)
  Developed TempSamp-R1 for reinforcement fine-tuning of video MLLMs. The framework achieved state-of-the-art temporal grounding results and enabled intelligent highlight detection and automated video editing in ByteDance/Volcano Engine VOD and live-streaming applications.