Submit a paper to Daily papers</p>\n","updatedAt":"2026-06-01T04:03:23.838Z","author":{"_id":"668f49e954a9166eda65d997","avatarUrl":"/avatars/afe67c9c40c99c124df507cf28530b97.svg","fullname":"wangjunlin","name":"HenryWJL","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.855233371257782},"editors":["HenryWJL"],"editorAvatarUrls":["/avatars/afe67c9c40c99c124df507cf28530b97.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.27919","authors":[{"_id":"6a186d289245bafffe463d1c","user":{"_id":"668f49e954a9166eda65d997","avatarUrl":"/avatars/afe67c9c40c99c124df507cf28530b97.svg","isPro":false,"fullname":"wangjunlin","user":"HenryWJL","type":"user","name":"HenryWJL"},"name":"Junlin Wang","status":"claimed_verified","statusLastChangedAt":"2026-05-29T09:33:51.775Z","hidden":false}],"publishedAt":"2026-05-27T00:00:00.000Z","submittedOnDailyAt":"2026-06-01T00:00:00.000Z","title":"Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal","submittedOnDailyBy":{"_id":"668f49e954a9166eda65d997","avatarUrl":"/avatars/afe67c9c40c99c124df507cf28530b97.svg","isPro":false,"fullname":"wangjunlin","user":"HenryWJL","type":"user","name":"HenryWJL"},"summary":"Learning visuomotor policies via behavior cloning typically involves mimicking expert demonstrations collected by human operators. However, natural human demonstrations inherently contain high-frequency noise, such as intermittent jerks, pauses, and action jitter. Training policies to directly imitate these raw trajectories inevitably causes the model to inherit these suboptimal behaviors. This pathology is particularly pronounced in diffusion-based policies, where iterative denoising steps can inadvertently amplify high-frequency artifacts at the expense of meaningful fine-grained details. To address these limitations, we present a novel frequency-based algorithm that enables implicit spectral maneuvering and smooth action generation. Our method, Frequency Guidance Operator (FGO), steers the generation process of diffusion polices by progressively driving the noisy samples through intermediate sub-frequency manifolds with expanding spectral bands. Validated on 15 robotic manipulation tasks from 5 benchmarks, FGO achieves superior performance in enhancing action smoothness and temporal consistency while preserving the details necessary for successful task execution. Project website: https://henrywjl.github.io/frequency-guidance-operator/","upvotes":0,"discussionId":"6a186d289245bafffe463d1d","projectPage":"https://henrywjl.github.io/frequency-guidance-operator/","githubRepo":"https://github.com/HenryWJL/fgo","githubRepoAddedBy":"user","ai_summary":"Frequency Guidance Operator enables smooth action generation in diffusion policies by steering noisy samples through intermediate sub-frequency manifolds, improving robotic manipulation performance.","ai_keywords":["behavior cloning","diffusion models","frequency guidance operator","spectral maneuvering","denoising steps","high-frequency noise","action smoothness","temporal consistency","robotic manipulation"],"githubStars":0,"organization":{"_id":"633cfd005d7b7741bef6aa99","name":"upenn","fullname":"University of Pennsylvania","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/FFSbROS6R8vPMIyXb7iIU.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"organization":{"_id":"633cfd005d7b7741bef6aa99","name":"upenn","fullname":"University of Pennsylvania","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/FFSbROS6R8vPMIyXb7iIU.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.27919.md"}">
Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
Abstract
Frequency Guidance Operator enables smooth action generation in diffusion policies by steering noisy samples through intermediate sub-frequency manifolds, improving robotic manipulation performance.
AI-generated summary
Learning visuomotor policies via behavior cloning typically involves mimicking expert demonstrations collected by human operators. However, natural human demonstrations inherently contain high-frequency noise, such as intermittent jerks, pauses, and action jitter. Training policies to directly imitate these raw trajectories inevitably causes the model to inherit these suboptimal behaviors. This pathology is particularly pronounced in diffusion-based policies, where iterative denoising steps can inadvertently amplify high-frequency artifacts at the expense of meaningful fine-grained details. To address these limitations, we present a novel frequency-based algorithm that enables implicit spectral maneuvering and smooth action generation. Our method, Frequency Guidance Operator (FGO), steers the generation process of diffusion polices by progressively driving the noisy samples through intermediate sub-frequency manifolds with expanding spectral bands. Validated on 15 robotic manipulation tasks from 5 benchmarks, FGO achieves superior performance in enhancing action smoothness and temporal consistency while preserving the details necessary for successful task execution. Project website: https://henrywjl.github.io/frequency-guidance-operator/
Community
Submit a paper to Daily papers
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.27919 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.27919 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.27919 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.