- SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis, ECCV 2024
- DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection, ICCV 2023
- From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds, ICRA 2023
- Training-Free Model Merging for Multi-target Domain Adaptation, ECCV 2024
Research Experience
- Generative Simulation for Embodied AI
- Data Efficient Scene Parsing, focusing on semi-supervised learning and domain adaptation
Education
- Bachelor's Degree: 2020 - 2024, Computer Science, Tsinghua University, GPA 3.98/4.00, ranked #1 in the department, received the highest distinction and SenseTime Scholarship
- Ph.D. Student: 2024 - Present, Computer Science, Tsinghua University, Advisor: Prof. Ya-Qin Zhang (Dean of Institute for AI Industry Research, AIR, THU)
Background
- Research Interests: LLM-based agents, multi-turn reinforcement learning, scalable reinforcement learning, evaluation of capability bottleneck in agent systems, self-evolution of agent systems
- Professional Field: Computer Science and Artificial Intelligence
Miscellany
- Co-Founder of Lumina-Embodied.AI community, bridging academic research with industry implementations
- Reviewer for multiple academic conferences and journals including CVPR, ICCV, WACV, 3DV, TPAMI, NeurIPS, etc.