CV

Education

• B.S. in Computer Science & Technology, Shanghai Jiao Tong University, 2017-2021
• M.S. in Computer Science, National University of Singapore, 2021-2024
• Ph.D in Computer Science & Engineering, The Chinese University of Hong Kong, 2024-2028 (expected)

Research Interests

• Multimodal Large Language Models
• Mixture of Experts
• Self-supervised Learning, Contrastive Learning
• Game Video Generation

Internship

• Tencent
  • User Behavior Analyst
  • May 2021 - Jul 2021
  • Enhanced the efficiency of the existing Neural Temporal Point Process-based user behavior analysis model
• Shanghai AI Laboratory
  • Research Assistant
  • Jan 2024 - Jul 2024
  • Research on multimodal large language model

Research Experience

• April 2019 - July 2021
  • ThinkLab, SJTU
  • Focus on Time Series Forecasting and Temporal Point Process
• Jun 2022 - July 2023
  • National University of Singapore
  • Focus on Self-supervised Learning, especially Contrastive Learning
• Jan 2023 - July 2024
  • Shanghai AI Laboratory
  • Focus on Multimodal Large Language Models

Publications

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning

Birds of a feather trust together: Knowing when to trust a classifier via adaptive neighborhood aggregation

EatingTrak: Detecting Fine-grained Eating Moments in the Wild Using a Wrist-mounted IMU

Learning generative RNN-ODE for collaborative time-series and event sequence forecasting

Synergetic learning of heterogeneous temporal sequences for multi-horizon probabilistic forecasting

Academic Service

Conference refereeing:

• NeurIPS 2024
• NeurIPS 2025
• ARR May 2025
• ICLR 2026