跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-14AI 評分36

互動影片生成中的推測式採樣

Speculative Sampling in Interactive Video Generation

AI 導讀

研究提出 Speculative Sampling,透過快取預測並逐步交付結果,讓互動影片生成採用較大的雙向窗口,降低延遲而不犧牲畫質。方法以噪聲 latents 作填充擴展建模窗口,並在條件不變時重用預測;尚未提交的未來預測仍可替換。這為互動串流系統部署大型雙向模型提供途徑,無須複雜的串流後訓練。

正文

Published on Oct 14

·

Submitted by

yuxuan

on Oct 15

Authors:

,

,

,

Abstract

Speculative Sampling enables interactive video generation with large bidirectional windows by caching predictions and delivering them incrementally, reducing latency without sacrificing quality.

Interactive video generation commonly relies on small bidirectional chunks to reduce response latency. Yet our preliminary experiments show that larger chunks improve video quality and better utilize GPU parallelism, allowing more latents to be sampled with only a modest increase in sampling time. Motivated by these observations, we propose Speculative Sampling, a strategy that combines the modeling power of large bidirectional windows with the low-latency interaction of small ones. It expands the modeling window by appending noise latents as padding and caches the resulting predictions for reuse when the condition remains unchanged. Predictions are delivered incrementally, while the uncommitted future remains replaceable. Our latency analysis shows that this removes the waiting-time lower bound imposed by chunk boundaries, shifting the optimization focus from reducing chunk size to accelerating per-chunk sampling. Bidirectional window size thus becomes a decision variable for jointly optimizing visual quality and sampling time, rather than a necessary constraint on low-latency interaction. This opens a path to serving large bidirectional models in interactive streaming systems without complex streaming post-training.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.20556

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.20556 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.20556 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.20556 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co