SoftVTBench: A Deformation-Aware Visuo-Tactile Dataset and Benchmark for Deformable-Object Manipulation</p>\n","updatedAt":"2026-08-20T03:37:17.073Z","author":{"_id":"686d185699645df570892710","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/zjMBsWvDnRSxSHe0yJC7h.png","fullname":"wangmingxinthu","name":"wangmingxinthu","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.38682419061660767},"editors":["wangmingxinthu"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/zjMBsWvDnRSxSHe0yJC7h.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.18701","authors":[{"_id":"6a867660db13816030683ee8","name":"Bowen Jing","hidden":false},{"_id":"6a867660db13816030683ee9","name":"Mingxin Wang","hidden":false},{"_id":"6a867660db13816030683eea","name":"Ruiyang Hao","hidden":false},{"_id":"6a867660db13816030683eeb","name":"Chenchen Ge","hidden":false},{"_id":"6a867660db13816030683eec","name":"Hanwen Shen","hidden":false},{"_id":"6a867660db13816030683eed","name":"Junjie He","hidden":false},{"_id":"6a867660db13816030683eee","name":"Yang Cui","hidden":false},{"_id":"6a867660db13816030683eef","name":"Yiming Hou","hidden":false},{"_id":"6a867660db13816030683ef0","name":"Weitao Zhou","hidden":false},{"_id":"6a867660db13816030683ef1","name":"Jiawei Wang","hidden":false},{"_id":"6a867660db13816030683ef2","name":"Minglei Li","hidden":false},{"_id":"6a867660db13816030683ef3","name":"Dandan Zhang","hidden":false},{"_id":"6a867660db13816030683ef4","name":"Ding Zhao","hidden":false},{"_id":"6a867660db13816030683ef5","name":"Houde Liu","hidden":false},{"_id":"6a867660db13816030683ef6","name":"Xiaofan Li","hidden":false},{"_id":"6a867660db13816030683ef7","name":"Si Liu","hidden":false},{"_id":"6a867660db13816030683ef8","name":"Ping Luo","hidden":false},{"_id":"6a867660db13816030683ef9","name":"Haibao Yu","hidden":false}],"publishedAt":"2026-08-19T00:00:00.000Z","submittedOnDailyAt":"2026-08-20T00:00:00.000Z","title":"SoftVTBench: A Deformation-Aware Visuo-Tactile Dataset and Benchmark for Deformable-Object Manipulation","submittedOnDailyBy":{"_id":"686d185699645df570892710","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/zjMBsWvDnRSxSHe0yJC7h.png","isPro":false,"fullname":"wangmingxinthu","user":"wangmingxinthu","type":"user","name":"wangmingxinthu"},"summary":"Physical interaction quality is central to deformable-object manipulation, yet most benchmarks evaluate task success alone. A policy may complete the task while allowing slip or causing excessive compression. A primary bottleneck is the absence of visuo-tactile datasets that pair policy-visible contact observations with independent physical ground truth over complete tasks. We introduce SoftVTBench, a visuo-tactile dataset for physical-interaction-aware deformable-object manipulation. It contains 4,000 expert demonstrations and more than 50 assets, including volumetric deformable objects and visually matched rigid twins. At 20 Hz, each episode synchronizes multi-view RGB, dual-finger tactile RGB and marker motion, proprioception, language, and binary and continuous gripper actions, alongside evaluator-only finite-element (FEM) states. Building upon this dataset, we establish a closed-loop benchmark that uses fixed object-specific calibration to define the Deformation-aware Success Rate (DSR), which counts a rollout as successful only when it completes the task and keeps peak normalized deformation within tolerance. Across Diffusion Policy, π_{0.5}, and FastWAM, all 12 in-distribution configurations contain successful rollouts that violate the deformation tolerance, accounting for 0.7--24% of each configuration's successes. Under distribution shift, visuo-tactile variants achieve higher task success in all six policy--suite comparisons and higher DSR in five, whereas their in-distribution benefits are mixed. These results show that making touch available does not by itself ensure effective multimodal fusion. SoftVTBench therefore provides a common visuo-tactile resource for studying not only whether a policy succeeds, but how it physically interacts with deformable objects and when touch improves that interaction.","upvotes":12,"discussionId":"6a867661db13816030683efa","ai_summary":"SoftVTBench introduces a synchronized visuo-tactile dataset and deformation-aware benchmark for evaluating physical interaction quality during deformable-object manipulation.","ai_keywords":["visuo-tactile dataset","deformable-object manipulation","diffusion policy","finite-element states","deformation-aware success rate","multimodal fusion"],"ai_summary_model":"thinkingmachines/Inkling-Small","organization":{"_id":"699963b744ef99f9e8f8a29b","name":"TuojingAI","fullname":"Tuojing Intelligence","avatar":"https://www.gravatar.com/avatar/5fe57a38cebe8624400a9cd5a2d47474?d=retro&size=100"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"686d185699645df570892710","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/zjMBsWvDnRSxSHe0yJC7h.png","isPro":false,"fullname":"wangmingxinthu","user":"wangmingxinthu","type":"user"},{"_id":"6a6a9a25a5b9c4c08baf22cb","avatarUrl":"/avatars/d3dbbe26cea0e3549d6051687e82fe4b.svg","isPro":false,"fullname":"Daniel Brown","user":"cobalttrail","type":"user"},{"_id":"6a6aa2d8df1718450cef87ed","avatarUrl":"/avatars/37b86fdbfaa48d5e154f84d8a232eb15.svg","isPro":false,"fullname":"Joseph Williams","user":"LunarNico","type":"user"},{"_id":"6a6c7ae91964ab520526751f","avatarUrl":"/avatars/3f9204fdb01c6cb2cae69af7a17d9f5f.svg","isPro":false,"fullname":"Charles Clark","user":"harborscope","type":"user"},{"_id":"6a6c858f217ea989952d4903","avatarUrl":"/avatars/3b91dcc188e129952493f3cad707e88a.svg","isPro":false,"fullname":"Michael Clark","user":"Quiet-Kai","type":"user"},{"_id":"6a6c88a68debfc3fc97a0507","avatarUrl":"/avatars/abd89b798629f991f50c36dea92795a8.svg","isPro":false,"fullname":"Elizabeth Gonzalez","user":"ElizabethGonzalez","type":"user"},{"_id":"6a6c9c7aa1aab08eb34a1057","avatarUrl":"/avatars/edc8e84ec7eb19de792c37266fe48176.svg","isPro":false,"fullname":"Patricia Wilson","user":"patricia-wilson","type":"user"},{"_id":"6a6dcab1e1c088f5242818bd","avatarUrl":"/avatars/16944b49b3a66aca9bf9ab88da508f79.svg","isPro":false,"fullname":"Sarah Brown","user":"PrismRidge","type":"user"},{"_id":"6a6de87ef9134eddf85d43da","avatarUrl":"/avatars/48a021580074a097f393f324bad012bb.svg","isPro":false,"fullname":"Timothy Lopez","user":"Silver-Timothy","type":"user"},{"_id":"6a70203ea0ffd1e23c37a4cc","avatarUrl":"/avatars/70371633c36487d2f305e0c3308c633e.svg","isPro":false,"fullname":"Mark Davis","user":"PrismArc","type":"user"},{"_id":"6a7d49b8ded3d695272a344a","avatarUrl":"/avatars/496bb9dda08b46bada2a8bb339ceb844.svg","isPro":false,"fullname":"Jennifer Wilson","user":"jennifer-wilson","type":"user"},{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"699963b744ef99f9e8f8a29b","name":"TuojingAI","fullname":"Tuojing Intelligence","avatar":"https://www.gravatar.com/avatar/5fe57a38cebe8624400a9cd5a2d47474?d=retro&size=100"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.18701.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.18701 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.18701 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.18701 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.