Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456 Paper page - Pathwise Test-Time Correction for Autoregressive Long Video Generation
\n","updatedAt":"2026-02-06T21:14:45.541Z","author":{"_id":"65243980050781c16f234f1f","avatarUrl":"/avatars/743a009681d5d554c27e04300db9f267.svg","fullname":"Avi","name":"avahal","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6946666240692139},"editors":["avahal"],"editorAvatarUrls":["/avatars/743a009681d5d554c27e04300db9f267.svg"],"reactions":[],"isReport":false}},{"id":"6986985ddf8c75f6dfbd4876","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2026-02-07T01:41:49.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path](https://huggingface.co/papers/2512.11203) (2025)\n* [HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming](https://huggingface.co/papers/2512.21338) (2025)\n* [Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention](https://huggingface.co/papers/2602.04789) (2026)\n* [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://huggingface.co/papers/2602.02214) (2026)\n* [End-to-End Training for Autoregressive Video Diffusion via Self-Resampling](https://huggingface.co/papers/2512.15702) (2025)\n* [JoyAvatar-Flash: Real-time and Infinite Audio-Driven Avatar Generation with Autoregressive Diffusion](https://huggingface.co/papers/2512.11423) (2025)\n* [Endless World: Real-Time 3D-Aware Long Video Generation](https://huggingface.co/papers/2512.12430) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\n
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
\n
If you want recommendations for any Paper on Hugging Face checkout this Space
\n
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
\n","updatedAt":"2026-02-07T01:41:49.092Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6247667670249939},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2602.05871","authors":[{"_id":"69855e014ad556f294b7eb4d","name":"Xunzhi Xiang","hidden":false},{"_id":"69855e014ad556f294b7eb4e","name":"Zixuan Duan","hidden":false},{"_id":"69855e014ad556f294b7eb4f","name":"Guiyu Zhang","hidden":false},{"_id":"69855e014ad556f294b7eb50","name":"Haiyu Zhang","hidden":false},{"_id":"69855e014ad556f294b7eb51","name":"Zhe Gao","hidden":false},{"_id":"69855e014ad556f294b7eb52","name":"Junta Wu","hidden":false},{"_id":"69855e014ad556f294b7eb53","name":"Shaofeng Zhang","hidden":false},{"_id":"69855e014ad556f294b7eb54","name":"Tengfei Wang","hidden":false},{"_id":"69855e014ad556f294b7eb55","name":"Qi Fan","hidden":false},{"_id":"69855e014ad556f294b7eb56","name":"Chunchao Guo","hidden":false}],"publishedAt":"2026-02-05T16:50:39.000Z","submittedOnDailyAt":"2026-02-06T00:50:53.322Z","title":"Pathwise Test-Time Correction for Autoregressive Long Video Generation","submittedOnDailyBy":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},"summary":"Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images or short clips, we identify that they fail to mitigate drift in extended sequences due to unstable reward landscapes and the hypersensitivity of distilled parameters. To overcome these limitations, we introduce Test-Time Correction (TTC), a training-free alternative. Specifically, TTC utilizes the initial frame as a stable reference anchor to calibrate intermediate stochastic states along the sampling trajectory. Extensive experiments demonstrate that our method seamlessly integrates with various distilled models, extending generation lengths with negligible overhead while matching the quality of resource-intensive training-based methods on 30-second benchmarks.","upvotes":3,"discussionId":"69855e014ad556f294b7eb57","ai_summary":"Test-Time Correction addresses error accumulation in distilled autoregressive diffusion models for long-video synthesis by using initial frames as reference anchors to calibrate stochastic states during sampling.","ai_keywords":["distilled autoregressive diffusion models","Test-Time Optimization","Test-Time Correction","error accumulation","long-sequence generation","reward landscapes","hypersensitivity","stochastic states","sampling trajectory"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"62e7c26236a8e8a827ff0891","avatarUrl":"/avatars/15648407233bf5757262dbc04464d02e.svg","isPro":false,"fullname":"Tengfei Wang","user":"tfwang","type":"user"},{"_id":"63ca8e060609f1def7e6548a","avatarUrl":"/avatars/1da7947840cb87d5f77c0af9ee11f9c2.svg","isPro":true,"fullname":"Yi Jung","user":"YJ-142150","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">
Test-Time Correction addresses error accumulation in distilled autoregressive diffusion models for long-video synthesis by using initial frames as reference anchors to calibrate stochastic states during sampling.
AI-generated summary
Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images or short clips, we identify that they fail to mitigate drift in extended sequences due to unstable reward landscapes and the hypersensitivity of distilled parameters. To overcome these limitations, we introduce Test-Time Correction (TTC), a training-free alternative. Specifically, TTC utilizes the initial frame as a stable reference anchor to calibrate intermediate stochastic states along the sampling trajectory. Extensive experiments demonstrate that our method seamlessly integrates with various distilled models, extending generation lengths with negligible overhead while matching the quality of resource-intensive training-based methods on 30-second benchmarks.
Introduces Test-Time Correction (TTC) to stabilize long autoregressive video generation by anchoring intermediate states to the initial frame, enabling longer sequences with minimal overhead.