Published papers: 'A Neural Symbolic Model for Space Physics' (Nature Machine Intelligence cover paper); 'MCU: An Evaluation Framework for Open-Ended Game Agents' (ICML Spotlight); 'TFG-Flow: Training-free Guidance in Multimodal Generative Flow' (ICLR); 'TFG: Unified Training-Free Guidance for Diffusion Models' (NeurIPS Spotlight); 'Selecting Large Language Model to Fine-tune via Rectified Scaling Law' (ICML); 'Class Incremental Learning via Likelihood Ratio-Based Task Prediction' (ICLR).
Research Experience
Worked with Prof. Bing Liu on OOD detection, continual learning, and NLP during undergraduate studies. Currently focuses on the foundations and applications of Generative Foundation Models (GFMs), including unification for multimodality, complex reasoning, open-world gaming, and discovering new laws in space physics. Member of Team CraftJarvis, dedicated to creating generalist agents for open-world environments.
Education
Bachelor's Degree: Yuanpei College, Peking University, majoring in Artificial Intelligence, advised by Prof. Bing Liu; Ph.D. Degree: Institute for Artificial Intelligence, Peking University, co-advised by Prof. Yitao Liang and Prof. Jianzhu Ma.
Background
Research Interests: Unification for multimodality and AI for scientific discovery. Field: Artificial Intelligence. Background: A third-year Ph.D. student at the Institute for Artificial Intelligence, Peking University, focusing on designing next-generation digital AI that deeply integrates into the real world.
Miscellany
Personal Interests: Engaging in music-related activities such as singing, playing the guitar, and participating in choirs.