Zhiying Xu — accepted AI-conference papers

2026

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

Haocheng Xi, Shuo Yang, Yilong Zhao, Muyang Li, Han Cai, Xingyang Li +10

ICML 2026poster

Despite rapid progress in auto-regressive video diffusion, we identify an emerging system–algorithm bottleneck that limits both deployability and generation quality: KV-cache memory. In auto-regressive video generation models, the KV-cache grows with generation history and quickly dominates GPU memo…

Cited by 0 Source ↗Scholar ↗

2025

FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point

Ke Yi, Jianwei Zhang, Zhiying Xu, Xinlong Yang, Yang Zhou, Minmin Sun +4

ACL 2025finding

Auto-regressive decoding is a memory-bound job, meaning decoding inference performance is limited by the bandwidth rather than the computational capabilities of the GPU. Weight-only quantization is a promising method to address the memory-bound limitations. Previous studies have followed one of two…

Cited by 0 Source ↗PDF ↗Scholar ↗