Experience
Alibaba · Qwen Business Group
Multimodal Research Intern, Visual Technology Department
Apr. 2026 – Present · Work with Jiaming Liu
- SyncPro: Proactive streaming video understanding with separate, synchronized thinking and response streams; trajectory construction, supervised fine-tuning, reinforcement learning, and evaluation.
- RARE: Reinforcement learning with adaptive rubric evolution for open-ended generation; reward design, model training, and evaluation on script generation and broader writing tasks.
ByteDance · Seed-Robotics
Research Intern, Multimodal LLMs for Robotics
Sept. 2024 – Apr. 2026
- Contributed to Robix, a unified model for robot interaction, reasoning, and planning.
- Curated approximately 130K robot task-planning examples and helped design and collect long-horizon mobile manipulation tasks in kitchen, supermarket, and tabletop settings.
- Developed consistency rewards and reward filtering for GRPO training to improve alignment between planning and execution.
Earlier experience
- Peking University, Research Intern, Jan. – Apr. 2022. Ubiquitous computing with Wi-Fi signals, advised by Prof. Daqing Zhang and Dr. Yang Li.
- China Agricultural University, Undergraduate Research Team Lead, Dec. 2019 – Mar. 2021. Ubiquitous computing for VR motion sickness.