- RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
- AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation
- TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
- Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
- M3Fair: Mitigating Bias in Healthcare Data through Multi-Level and Multi-Sensitive Attribute Reweighting Method
Awards:
- 2023 Grand Prize (Top 1) in 'Challenge Cup' National Competition
- 2023 NIH Bias Detection Third Prize (Top 5)
Research Experience
2025.02 - Present School of Computer Science at Peking University Research Intern Research Advisors: Dr. Cheng Chi, Prof. Shanghang Zhang
2023.12 - 2024.08 School of Electronics Engineering and Computer Science at Peking University Research Intern Research Advisors: Dr. Yemin Shi, Prof. Li Yuan
Education
2020.09 - 2024.06 Beihang University Bachelor of Software Engineering GPA ranking: 27/187 Research Advisor: Prof. Chengwei Pan
Background
Research Interests: Embodied Agents, particularly at the intersection of Multimodal Large Language Models and Embodied AI, with a focus on high-level planning and low-level control with spatio-temporal intelligence.
Miscellany
This homepage is designed based on Jon Barron's website.