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

The following papers were recommended by the Semantic Scholar API

Towards Cross-View Point Correspondence in Vision-Language Models (2025)
Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation (2026)
MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images (2025)
Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos (2025)
SpatialMosaic: A Multiview VLM Dataset for Partial Visibility (2025)
Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training (2025)
From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs (2025)

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":"2026-01-23T01:36:45.286Z","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":0.7454103231430054},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2601.14352","authors":[{"_id":"697197e3c1c7409747bf95bb","user":{"_id":"66b5dc0b854ad316cf835ab4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66b5dc0b854ad316cf835ab4/8gOWw81rV5la7mzjw_qRv.jpeg","isPro":false,"fullname":"tanhuajie2001","user":"tanhuajie2001","type":"user"},"name":"Huajie Tan","status":"claimed_verified","statusLastChangedAt":"2026-01-26T08:33:17.636Z","hidden":false},{"_id":"697197e3c1c7409747bf95bc","user":{"_id":"63f08dc79cf89c9ed1bb89cd","avatarUrl":"/avatars/37290358ad00bbd752f519cfdec02f3e.svg","isPro":false,"fullname":"Zhoues","user":"Zhoues","type":"user"},"name":"Enshen Zhou","status":"claimed_verified","statusLastChangedAt":"2026-01-22T08:45:02.013Z","hidden":false},{"_id":"697197e3c1c7409747bf95bd","name":"Zhiyu Li","hidden":false},{"_id":"697197e3c1c7409747bf95be","name":"Yijie Xu","hidden":false},{"_id":"697197e3c1c7409747bf95bf","name":"Yuheng Ji","hidden":false},{"_id":"697197e3c1c7409747bf95c0","name":"Xiansheng Chen","hidden":false},{"_id":"697197e3c1c7409747bf95c1","name":"Cheng Chi","hidden":false},{"_id":"697197e3c1c7409747bf95c2","name":"Pengwei Wang","hidden":false},{"_id":"697197e3c1c7409747bf95c3","name":"Huizhu Jia","hidden":false},{"_id":"697197e3c1c7409747bf95c4","name":"Yulong Ao","hidden":false},{"_id":"697197e3c1c7409747bf95c5","name":"Mingyu Cao","hidden":false},{"_id":"697197e3c1c7409747bf95c6","name":"Sixiang Chen","hidden":false},{"_id":"697197e3c1c7409747bf95c7","name":"Zhe Li","hidden":false},{"_id":"697197e3c1c7409747bf95c8","name":"Mengzhen Liu","hidden":false},{"_id":"697197e3c1c7409747bf95c9","name":"Zixiao Wang","hidden":false},{"_id":"697197e3c1c7409747bf95ca","name":"Shanyu Rong","hidden":false},{"_id":"697197e3c1c7409747bf95cb","name":"Yaoxu Lyu","hidden":false},{"_id":"697197e3c1c7409747bf95cc","name":"Zhongxia Zhao","hidden":false},{"_id":"697197e3c1c7409747bf95cd","name":"Peterson Co","hidden":false},{"_id":"697197e3c1c7409747bf95ce","name":"Yibo Li","hidden":false},{"_id":"697197e3c1c7409747bf95cf","name":"Yi Han","hidden":false},{"_id":"697197e3c1c7409747bf95d0","name":"Shaoxuan Xie","hidden":false},{"_id":"697197e3c1c7409747bf95d1","name":"Guocai Yao","hidden":false},{"_id":"697197e3c1c7409747bf95d2","name":"Songjing Wang","hidden":false},{"_id":"697197e3c1c7409747bf95d3","name":"Leiduo Zhang","hidden":false},{"_id":"697197e3c1c7409747bf95d4","name":"Xi Yang","hidden":false},{"_id":"697197e3c1c7409747bf95d5","name":"Yance Jiao","hidden":false},{"_id":"697197e3c1c7409747bf95d6","name":"Donghai Shi","hidden":false},{"_id":"697197e3c1c7409747bf95d7","name":"Kunchang Xie","hidden":false},{"_id":"697197e3c1c7409747bf95d8","name":"Shaokai Nie","hidden":false},{"_id":"697197e3c1c7409747bf95d9","name":"Chunlei Men","hidden":false},{"_id":"697197e3c1c7409747bf95da","name":"Yonghua Lin","hidden":false},{"_id":"697197e3c1c7409747bf95db","name":"Zhongyuan Wang","hidden":false},{"_id":"697197e3c1c7409747bf95dc","name":"Tiejun Huang","hidden":false},{"_id":"697197e3c1c7409747bf95dd","name":"Shanghang Zhang","hidden":false}],"publishedAt":"2026-01-20T17:21:54.000Z","submittedOnDailyAt":"2026-01-22T00:52:27.595Z","title":"RoboBrain 2.5: Depth in Sight, Time in Mind","submittedOnDailyBy":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},"summary":"We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative grounding to depth-aware coordinate prediction and absolute metric constraint comprehension, generating complete 3D manipulation traces as ordered keypoint sequences under physical constraints. Complementing this spatial precision, the model establishes Dense Temporal Value Estimation that provides dense, step-aware progress prediction and execution state understanding across varying viewpoints, producing stable feedback signals for downstream learning. Together, these upgrades extend the framework toward more physically grounded and execution-aware embodied intelligence for complex, fine-grained manipulation. The code and checkpoints are available at project website: https://superrobobrain.github.io","upvotes":11,"discussionId":"697197e3c1c7409747bf95de","projectPage":"https://superrobobrain.github.io/","ai_summary":"RoboBrain 2.5 enhances embodied AI through improved 3D spatial reasoning and temporal value estimation for more precise manipulation tasks.","ai_keywords":["embodied AI","spatiotemporal supervision","3D spatial reasoning","depth-aware coordinate prediction","metric constraint comprehension","3D manipulation traces","temporal value estimation","step-aware progress prediction","execution state understanding"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6342796a0875f2c99cfd313b","avatarUrl":"/avatars/98575092404c4197b20c929a6499a015.svg","isPro":false,"fullname":"Yuseung \"Phillip\" Lee","user":"phillipinseoul","type":"user"},{"_id":"63f08dc79cf89c9ed1bb89cd","avatarUrl":"/avatars/37290358ad00bbd752f519cfdec02f3e.svg","isPro":false,"fullname":"Zhoues","user":"Zhoues","type":"user"},{"_id":"65ec01fd770aa0e25d9374dc","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65ec01fd770aa0e25d9374dc/yvLWwBEdAdHb-8EdUHg3n.jpeg","isPro":false,"fullname":"Shijie Lian","user":"LiamLian0727","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","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"},{"_id":"684d57f26e04c265777ead3f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/cuOj-bQqukSZreXgUJlfm.png","isPro":false,"fullname":"Joakim Lee","user":"Reinforcement4All","type":"user"},{"_id":"66b5dc0b854ad316cf835ab4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66b5dc0b854ad316cf835ab4/8gOWw81rV5la7mzjw_qRv.jpeg","isPro":false,"fullname":"tanhuajie2001","user":"tanhuajie2001","type":"user"},{"_id":"675dd24a2c98629a5e49dfac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/tI3V8-PZ8d3CC32fzO31e.png","isPro":false,"fullname":"Starstrek","user":"Stars321123","type":"user"},{"_id":"63c1699e40a26dd2db32400d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63c1699e40a26dd2db32400d/3N0-Zp8igv8-52mXAdiiq.jpeg","isPro":false,"fullname":"Chroma","user":"Chroma111","type":"user"},{"_id":"67a621a777d94969c979dade","avatarUrl":"/avatars/b693d6648b590fd52823fc297749149f.svg","isPro":false,"fullname":"Dipan Maity","user":"DipanM2","type":"user"},{"_id":"64c0c5b6f6d4c1e5cf97bfc0","avatarUrl":"/avatars/d3b81513ce4a7318e4002b0428b96aa9.svg","isPro":false,"fullname":"Allen Wei","user":"A113NW3I","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2601.14352

RoboBrain 2.5: Depth in Sight, Time in Mind

Published on Jan 20

· Submitted by

taesiri on Jan 22

Upvote

Authors:

Huajie Tan ,

Enshen Zhou ,

Abstract

RoboBrain 2.5 enhances embodied AI through improved 3D spatial reasoning and temporal value estimation for more precise manipulation tasks.

AI-generated summary

We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative grounding to depth-aware coordinate prediction and absolute metric constraint comprehension, generating complete 3D manipulation traces as ordered keypoint sequences under physical constraints. Complementing this spatial precision, the model establishes Dense Temporal Value Estimation that provides dense, step-aware progress prediction and execution state understanding across varying viewpoints, producing stable feedback signals for downstream learning. Together, these upgrades extend the framework toward more physically grounded and execution-aware embodied intelligence for complex, fine-grained manipulation. The code and checkpoints are available at project website: https://superrobobrain.github.io