500AI
← People

Xuyang Liu

Source-listed: First-year PhD student · The Hong Kong Polytechnic University (PolyU)

  • Multimodal AI
  • Language models
  • Efficient ML

Selected work

5
  1. Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language ModelsFirst author · 2025
  2. Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language ModelsFirst author · 2026
  3. Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language ModelsFirst author · 2026
  4. Accelerating Diffusion Transformers with Token-wise Feature CachingFirst author · 2025
  5. V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning BenchmarkFirst author · 2024