Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
The paper introduces the Autoregressive Video Inverse problem Solver (AVIS), which aims to enhance the efficiency of video restoration using autoregressive diffusion models. AVIS significantly reduces initial latency and increases throughput compared to existing methods, making it suitable for real-time applications. An accelerated variant, AVIS Flash, further improves performance while maintaining quality, paving the way for practical deployment.
- ▪AVIS reduces initial latency from 114 seconds to 4 seconds.
- ▪Throughput increases from 0.71 to 1.18 frames per second (FPS) with AVIS.
- ▪AVIS Flash boosts throughput to 5.91 FPS on a single RTX 4090 GPU.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20624 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | FM2-6bJ_tnFt |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computer Vision and Pattern Recognition arXiv:2605.20624 (cs) [Submitted on 20 May 2026] Title:Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models Authors:Taesung Kwon, Jonghyun Park, Hyungjin Chung, Jong Chul Ye View a PDF of the paper titled Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models, by Taesung Kwon and 3 other authors View PDF HTML (experimental) Abstract:Diffusion models provide powerful priors for zero-shot video inverse problems, but their real-time deployment is hindered by two inefficiencies: high initial latency caused by holistic video restoration, and low throughput resulting from multiple VAE passes to enforce measurement consistency in pixel space.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
