Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2026-01-16T01:37:47.831Z","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":0.709808886051178},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2601.01075","authors":[{"_id":"69693de932f0333869ff9357","user":{"_id":"63c7a750bce33b25442a400d","avatarUrl":"/avatars/2f95b30f0dc6a70725741d4b8d35f1f8.svg","isPro":false,"fullname":"Hansen Lillemark","user":"hlillemark","type":"user"},"name":"Hansen Jin Lillemark","status":"claimed_verified","statusLastChangedAt":"2026-01-16T10:30:54.847Z","hidden":false},{"_id":"69693de932f0333869ff9358","user":{"_id":"64b22e6b0a54158d66f18688","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b22e6b0a54158d66f18688/Cbl3oMMMANbnCMoSUYenI.png","isPro":true,"fullname":"Benhao Huang","user":"HuskyDoge","type":"user"},"name":"Benhao Huang","status":"claimed_verified","statusLastChangedAt":"2026-01-16T10:30:56.765Z","hidden":false},{"_id":"69693de932f0333869ff9359","name":"Fangneng Zhan","hidden":false},{"_id":"69693de932f0333869ff935a","name":"Yilun Du","hidden":false},{"_id":"69693de932f0333869ff935b","name":"Thomas Anderson Keller","hidden":false}],"publishedAt":"2026-01-03T05:22:27.000Z","submittedOnDailyAt":"2026-01-15T16:54:28.180Z","title":"Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments","submittedOnDailyBy":{"_id":"64b22e6b0a54158d66f18688","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b22e6b0a54158d66f18688/Cbl3oMMMANbnCMoSUYenI.png","isPro":true,"fullname":"Benhao Huang","user":"HuskyDoge","type":"user"},"summary":"Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-motion, interwoven with the dynamics of external objects. These streams obey smooth, time-parameterized symmetries, which combine through a precisely structured algebra; yet most neural network world models ignore this structure and instead repeatedly re-learn the same transformations from data. In this work, we introduce 'Flow Equivariant World Models', a framework in which both self-motion and external object motion are unified as one-parameter Lie group 'flows'. We leverage this unification to implement group equivariance with respect to these transformations, thereby providing a stable latent world representation over hundreds of timesteps. On both 2D and 3D partially observed video world modeling benchmarks, we demonstrate that Flow Equivariant World Models significantly outperform comparable state-of-the-art diffusion-based and memory-augmented world modeling architectures -- particularly when there are predictable world dynamics outside the agent's current field of view. We show that flow equivariance is particularly beneficial for long rollouts, generalizing far beyond the training horizon. By structuring world model representations with respect to internal and external motion, flow equivariance charts a scalable route to data efficient, symmetry-guided, embodied intelligence. Project link: https://flowequivariantworldmodels.github.io.","upvotes":6,"discussionId":"69693de932f0333869ff935c","projectPage":"https://flowequivariantworldmodels.github.io/","githubRepo":"https://github.com/hlillemark/flowm","githubRepoAddedBy":"auto","ai_summary":"Flow Equivariant World Models unify self-motion and external object motion as one-parameter Lie group flows to create stable, symmetry-guided representations for embodied intelligence.","ai_keywords":["world models","Lie group flows","group equivariance","embodied systems","sensory input","time-parameterized symmetries","latent world representation","diffusion-based models","memory-augmented architectures","long rollouts","data efficiency"],"githubStars":31},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64b22e6b0a54158d66f18688","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b22e6b0a54158d66f18688/Cbl3oMMMANbnCMoSUYenI.png","isPro":true,"fullname":"Benhao Huang","user":"HuskyDoge","type":"user"},{"_id":"64b19c349826b935a2aeca6d","avatarUrl":"/avatars/a29bf5c4989c1c07b571c0c2061d43c3.svg","isPro":false,"fullname":"Fangneng Zhan","user":"fnzhan","type":"user"},{"_id":"63c7a750bce33b25442a400d","avatarUrl":"/avatars/2f95b30f0dc6a70725741d4b8d35f1f8.svg","isPro":false,"fullname":"Hansen Lillemark","user":"hlillemark","type":"user"},{"_id":"6312cab05beb528b5c1500e3","avatarUrl":"/avatars/a328e8cc99fb031b2d5c911c4b577e7e.svg","isPro":false,"fullname":"Fu-En Yang","user":"FuEnYang","type":"user"},{"_id":"68a74579646ad764c5cafd71","avatarUrl":"/avatars/3cb44f4373d708e5c397dd4814a716eb.svg","isPro":false,"fullname":"MihailSlutsky","user":"MihailSlutsky","type":"user"},{"_id":"686db5d4af2b856fabbf13aa","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/6BjMv2LVNoqvbX8fQSTPI.png","isPro":false,"fullname":"V bbbb","user":"Bbbbbnnn","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2601.01075

Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments

Published on Jan 3

· Submitted by

Benhao Huang on Jan 15

Upvote

Authors:

Hansen Jin Lillemark ,

Benhao Huang ,

Abstract

Flow Equivariant World Models unify self-motion and external object motion as one-parameter Lie group flows to create stable, symmetry-guided representations for embodied intelligence.

AI-generated summary

Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-motion, interwoven with the dynamics of external objects. These streams obey smooth, time-parameterized symmetries, which combine through a precisely structured algebra; yet most neural network world models ignore this structure and instead repeatedly re-learn the same transformations from data. In this work, we introduce 'Flow Equivariant World Models', a framework in which both self-motion and external object motion are unified as one-parameter Lie group 'flows'. We leverage this unification to implement group equivariance with respect to these transformations, thereby providing a stable latent world representation over hundreds of timesteps. On both 2D and 3D partially observed video world modeling benchmarks, we demonstrate that Flow Equivariant World Models significantly outperform comparable state-of-the-art diffusion-based and memory-augmented world modeling architectures -- particularly when there are predictable world dynamics outside the agent's current field of view. We show that flow equivariance is particularly beneficial for long rollouts, generalizing far beyond the training horizon. By structuring world model representations with respect to internal and external motion, flow equivariance charts a scalable route to data efficient, symmetry-guided, embodied intelligence. Project link: https://flowequivariantworldmodels.github.io.