Research

PhD Candidate at Beihang University, specializing in neural network compression and model quantization. Making deep learning more efficient and accessible for real-world deployment.

Research Focus

  • Efficient inference and deployment for large language models and MoE models.
  • Post-training compression and acceleration, e.g., quantization, pruning, kv cache and decoding optimization.
  • High-performance operators and kernels for low-bit, sparse, and hardware-aware computation.
  • Multimodal understanding and generation, including vision-language models and image/video diffusion models.

Ongoing Projects

  • Clinical World Model for physiological forecasting.
  • Real-time quantum error correction with customized FPGA.
  • Deployment-friendly multimodal MoE compression.
  • Super-resolution diffusion acceleration for image generation.

Selected Publications

All Publications

Filter Rules Cleared!
Sort by Year
View publications on Google Scholar →