Poster · Sydney
FocusVLA: Hijacking Attention to Break Visual Token Pruning in Vision-Language-Action Models
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Yanhui Li, Qianpu Sun, Qi Zhou, Chenru Jiang, Peiyu Zhang, Dongxia Wang
- Organisations
- Zhejiang University, Tsinghua University, Duke University, Xtalpi Inc
- QRS classification
- Attention and transformers, Language models, Computer vision, Efficient and distributed ML systems