Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

QuantWM targets flicker in 2-bit video-world-model caches

AI summary

Researchers from iLearn-Lab at Harbin Institute of Technology (Shenzhen) and LV-Lab at the National University of Singapore propose QuantWM, a training-free framework for 2-bit KV Cache quantization in video world models. The team says its query-sensitive clustering and low-rank attention compensation improve visual stability while achieving up to 6.20x KV Cache compression across five evaluated models.

In-depth insight

The work highlights that standard video metrics may miss temporal instability caused by low-bit KV Cache quantization.

机器之心 2026-10-07 09:49 北京

评测分数不代表一切。

视频世界模型(Video World Model)需要生成连续画面,并在用户指定动作的控制下维持场景一致性。对于基于自回归生成的视频世界模型,KV Cache 中保存着历史画面,使得生成时能够检索并重复利用此前生成的相似场景。然而随着生成的不断进行,KV Cache 的显存成本十分高昂。例如 LingBot-World-v2 生成约 5 秒、93 帧的视频,KV Cache 就需要超过 21 GiB 显存。

将 KV Cache 量化到 2-bit 是缓解这一问题的重要方向,目前已有方法将 2-bit KV Cache 量化应用于自回归视频生成,并取得接近 BF16 的 VBench 评测表现。但研究团队发现,当将这些方法应用于视频世界模型时,即使评测分数几乎不变,生成画面仍可能出现明显的闪烁、模糊和细节失真。

#QuantWM#iLearn-Lab#Harbin Institute of Technology (Shenzhen)#LV-Lab#National University of Singapore#LingBot-World-v2#HY-World 1.5#Matrix-Game-2#LongCat-Video#Causal-Forcing#Quant-VideoGen#KIVI

Original · 6 min readRead the original
Group chat

No comments yet. Start the conversation.