Jenq-Neng Hwang

Full Professor, University of Washington, Seattle

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

#3406 · Kunjun Li, Zigeng Chen, Cheng-Yen Yang, Jenq-Neng Hwang

We efficetively address the resolution scalability challenge caused by exponential growth in token sequences in VAR models, while preserving pixel-level fidelity.