← Back to all news
arXiv Computer Vision By Hyunwook Choi, Seungryong Kim, Dongyoon Han, Sangdoo Yun

Speculative Forcing for Efficient Autoregressive Video Generation

Read the original on arXiv Computer Vision →

Speculative Forcing is a framework for efficient autoregressive video generation that treats intermediate clean estimates as drafts and predicts when individual tokens can be safely accepted early. Tokens that are accepted are frozen and no longer undergo further denoising, while their cached keys and values remain available for context. Two verifier designs—one training‑free based on similarity and stability, and one learned that uses intermediate features—enable this selective refinement, preserving full‑step quality while reducing computation across short‑video, long‑video, and world generation tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Oct 1

In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion

arXiv:2609.32540v2 Announce Type: replace-cross Abstract: Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, eac...

By Yikai Wang, Xiao Han, Mengmeng Xu, Juan Camilo Perez, Yiannis Douratsos, Sen He, Zijian Zhou, Fei Zhang, Zhaochong An, Juan-Manuel Perez-Rua, Chen Change Loy, Tao Xiang
diffusionefficiency
More like this →
arXiv AI
1d ago

RECAP: Context-Aware Prediction Recycling with Request-Local and Persistent Memories for Multimodal Speculative Decoding

The paper introduces RECAP, a method that improves speculative decoding for vision‑language models by recycling a target model’s own predictions. RECAP stores predictions using one‑, two‑, and three‑token keys, allowing contextual memories that are request‑specific and token‑level memories that persist across requests. By fusing retrieved predictions based on entropy‑confidence weighting and using best‑first search to build a candidate tree, RECAP achieves significant speedups over autoregressive decoding without requiring training or a draft model.

By Hengjie Zhu, Dayan Wu, Xinze Liu, Peng Fu, Zheng Lin, Weiping Wang
llmsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Oct 5

In-Distribution Forcing for Long Video Generation at Test Time

In-Distribution Forcing for Long Video Generation at Test Time introduces a test‑time framework that aligns KV caching and conditioning with training configurations to prevent out‑of‑distribution key‑value entries during long‑horizon video generation. The core technique, self‑caching, ensures each chunk is cached without attending to prior KV entries, keeping the rolling window exactly in‑distribution. This approach extends short‑horizon autoregressive video diffusion models to minute‑scale generation, outperforming prior methods in mitigating drifting as shown by drift metrics and a user study.

By Jeongwoo Shin, Youngyoon Choi, Sangwoo Jo, Hyunmog Kim, Sungjoon Choi, Joonseok Lee, Jaewoong Choi, Jaemoo Choi
diffusionbenchmarks
More like this →