Xuyang Liu
Source-listed: First-year PhD student · The Hong Kong Polytechnic University (PolyU)
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language ModelsSaved credit: First author · 2025Explore people connected to this work →
- Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language ModelsSaved credit: First author · 2026Explore people connected to this work →
- Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language ModelsSaved credit: First author · 2026Explore people connected to this work →
- Accelerating Diffusion Transformers with Token-wise Feature CachingSaved credit: First author · 2025Explore people connected to this work →
- V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning BenchmarkSaved credit: First author · 2024Explore people connected to this work →