Poster · Sydney
SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Chen Qian, Xinran Yu, Xinan Wang, Danyang Li, Guoxuan Chi, Zheng Yang, Qiang Ma, Xin Miao
- Organisations
- Tsinghua University, Beijing University of Posts and Telecommunications
- QRS classification
- Language models, Computer vision