⚙️ Experience

Research Intern @ Qwen Team, Alibaba Group Mar 2025 – Oct 2025   |   Beijing, China

• Built an evaluation framework for VLM4VLA, validating vision-language models on robotic operation tasks.
• Qwen3-VL Technical Report: contributor to Qwen3-VL project, participated in enhancing embodied understanding in VLMs, including data collection and processing with spatial-position annotations from embodied tasks.

Research Intern @ Seed Robotics, ByteDance Group Oct 2025 – May 2026   |   Beijing, China

• BagelVLA: large unified MLLM in VLA with Bagel for long-horizon manipulation, covering understanding, world modeling, and robotic control.
• UAM: explored how unified models and world models interact with actions in VLA training, providing a dual-stream perspective on forgetting and guidance for next-generation VLA design.