Poster · Atlanta

VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation

Name: VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
Start: 2026-12-10T10:00:00-05:00
End: 2026-12-10T13:00:00-05:00
Location: Hall C1, Georgia World Congress Center

When: Thu 10 Dec 2026, 10:00–13:00 EST
Where: Hall C1, Georgia World Congress Center
Session: Atlanta Poster Session 3
Authors: Boxun Xu, Jiaji Lu, Yuxuan Yin, Zihu Wang, Ziyue (Alvin) Liu, Yu Wang, Zirui Liu, Peng Li
Organisations: Meta, University of California, Santa Barbara, Amazon, University of Minnesota
QRS classification: Generative models, Computer vision, Efficient and distributed ML systems

Open in schedule Official page