Experiences

Work Experiences

• Debiased Imitation Learning for Modulated Temporal Point Processes[code]
  
  • Model biased event sequences as modulating TPPs with additional unknown thinning processes.
    
  • Develop a novel debiased imitation learning framework to learn the modulated TPPs.
    
  • Design a simple but effective reward function based on the historical embedding.
    
• Sparse Transformer Hawkes Process for Long Event Sequences[code]
  
  • Design a novel temporal sparse self-attention mechanism for event sequences with arbitrary intervals.
    
  • Proposed a two-level transformer model to capture both the short-term and long-term information.
    
• Virtual File System[code]
  
  • Develop a tree-structured virtual file system tailored for the Linux operating system .
    
  • Enables real-time file transfer between the client and server.