\n\t<a id=\"eva-client-one-client-full-cycle\" class=\"block pr-1.5 text-lg md:absolute md:p-1.5 md:opacity-0 md:group-hover:opacity-100 md:right-full\" href=\"#eva-client-one-client-full-cycle\" rel=\"nofollow\">\n\t\t<span class=\"header-link\"><svg class=\"text-gray-500 hover:text-black dark:hover:text-gray-200 w-4\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" aria-hidden=\"true\" role=\"img\" width=\"1em\" height=\"1em\" preserveAspectRatio=\"xMidYMid meet\" viewBox=\"0 0 256 256\"><path d=\"M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z\" fill=\"currentColor\"></path></svg></span>\n\t</a>\n\t<span>\n\t\tEVA-Client: One Client, Full Cycle\n\t</span>\n</h3>\n<p>For robot policies, training frameworks have converged: OpenPI, LeRobot, StarVLA, and VLA Foundry solve much of the training-side stack. The real-robot side should not still be a patchwork of project-specific scripts. EVA-Client fills that missing infrastructure for embodied-policy iteration: collect teleop data, inspect and prepare datasets, deploy checkpoints, compensate latency, smooth trajectories, run model evaluations, compare logs, and feed results back into the next training round. One client covers the full real-robot iteration cycle.</p>\n<p>Project Page: <a href=\"https://colalab.net/projects/eva-client/\" rel=\"nofollow\">https://colalab.net/projects/eva-client/</a><br>Code: <a href=\"https://github.com/Noietch/EVA-CLIENT\" rel=\"nofollow\">https://github.com/Noietch/EVA-CLIENT</a></p>\n","updatedAt":"2026-07-07T04:19:56.358Z","author":{"_id":"65fc7c824d36be78e66ba92d","avatarUrl":"/avatars/d4a55c820cae533f91724e062427516a.svg","fullname":"Linjiang Huang","name":"LjHuang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8682920336723328},"editors":["LjHuang"],"editorAvatarUrls":["/avatars/d4a55c820cae533f91724e062427516a.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.02646","authors":[{"_id":"6a4c791e25849b193a83417c","name":"Heqing Yang","hidden":false},{"_id":"6a4c791e25849b193a83417d","name":"Yang Yi","hidden":false},{"_id":"6a4c791e25849b193a83417e","name":"Liyao Wang","hidden":false},{"_id":"6a4c791e25849b193a83417f","name":"Linqing Zhong","hidden":false},{"_id":"6a4c791e25849b193a834180","name":"Donglin Yang","hidden":false},{"_id":"6a4c791e25849b193a834181","name":"Ruipu Wu","hidden":false},{"_id":"6a4c791e25849b193a834182","name":"Zitong Bai","hidden":false},{"_id":"6a4c791e25849b193a834183","name":"Fengjiao Chen","hidden":false},{"_id":"6a4c791e25849b193a834184","name":"Manyuan Zhang","hidden":false},{"_id":"6a4c791e25849b193a834185","name":"Linjiang Huang","hidden":false},{"_id":"6a4c791e25849b193a834186","name":"Si Liu","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/65fc7c824d36be78e66ba92d/WGaseoy5VE0a1kyLjbuYg.mp4"],"publishedAt":"2026-07-02T00:00:00.000Z","submittedOnDailyAt":"2026-07-07T00:00:00.000Z","title":"EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots","submittedOnDailyBy":{"_id":"65fc7c824d36be78e66ba92d","avatarUrl":"/avatars/d4a55c820cae533f91724e062427516a.svg","isPro":false,"fullname":"Linjiang Huang","user":"LjHuang","type":"user","name":"LjHuang"},"summary":"We present EVA-Client, an open-source framework for deployment, data collection, and evaluation of trained manipulation policies on real robots. Sitting between a policy server and the physical hardware, EVA-Client unifies the real-robot stages of the policy iteration loop within a single codebase. It makes three contributions. First, a component-decoupled architecture in which robot backends, inference strategies, and transport middlewares form an orthogonal grid: adding a robot or a strategy touches only its own layer. Second, inspectable execution through Debug, Collect, and Eval workflows, with modes ranging from open-loop simulation to continuous real-time control. Third, every evaluation run doubles as a data collection, recording full rollouts in training-ready format alongside exhaustive logs and a side-by-side comparison viewer, so each evaluation feeds the next round of training rather than ending as an unrecorded impression. EVA-Client further consolidates major real-time inference strategies, synchronous and asynchronous execution, ACT-style temporal ensembling, Real-Time Chunking, and a naive-async ablation baseline, behind a single configuration surface.","upvotes":23,"discussionId":"6a4c791e25849b193a834187","projectPage":"https://colalab.net/projects/eva-client/","githubRepo":"https://github.com/Noietch/EVA-CLIENT","githubRepoAddedBy":"user","ai_summary":"EVA-Client is an open-source framework that unifies real-robot policy deployment, data collection, and evaluation through a component-decoupled architecture with inspectable execution workflows.","ai_keywords":["policy iteration loop","robot backends","inference strategies","transport middlewares","debug workflow","collect workflow","eval workflow","real-time control","synchronous execution","asynchronous execution","temporal ensembling","real-time chunking","naive-async ablation baseline"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":40},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65fc7c824d36be78e66ba92d","avatarUrl":"/avatars/d4a55c820cae533f91724e062427516a.svg","isPro":false,"fullname":"Linjiang Huang","user":"LjHuang","type":"user"},{"_id":"64fae0310e486522f8103d98","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64fae0310e486522f8103d98/OJlPuQQ5OXeu13-3muiVY.jpeg","isPro":false,"fullname":"yangheqing","user":"Noietch","type":"user"},{"_id":"642cf9a6ad221e8f41d3e0d0","avatarUrl":"/avatars/5fed346e20870a697864af3975aef8c0.svg","isPro":false,"fullname":"Kaining Ying","user":"Kaining","type":"user"},{"_id":"64e819f2c5c7caadabf1c243","avatarUrl":"/avatars/d65fc6ba6b5e76c58ef384f9f117fff2.svg","isPro":false,"fullname":"yangdonglin","user":"puffyyy","type":"user"},{"_id":"6a4c7fe6db3e33443c8be98c","avatarUrl":"/avatars/d9113fe684e8e71c765634367a72a06d.svg","isPro":false,"fullname":"Zitong Bai","user":"ZitongBai","type":"user"},{"_id":"69ba22f68479cd8908074a13","avatarUrl":"/avatars/c832bee66c87c9d2864096ef89bb41ee.svg","isPro":false,"fullname":"a","user":"y2027","type":"user"},{"_id":"6428fd124fe87caede856311","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/5OrNPwZkxu3Dm1IInCxML.jpeg","isPro":false,"fullname":"Xianghao Kong","user":"refkxh","type":"user"},{"_id":"67544083481dae41e89064bd","avatarUrl":"/avatars/0e798892953c8279fb32b92189ae28d1.svg","isPro":false,"fullname":"闫思桥","user":"Cloud-Iris","type":"user"},{"_id":"6600e2437561dddeb77c4fb5","avatarUrl":"/avatars/c2fac507ef287f738ef7ab16fa55c5b4.svg","isPro":false,"fullname":"jinweilin","user":"wkinglin","type":"user"},{"_id":"64b6abe17f3490ffe72071d0","avatarUrl":"/avatars/9d1b7ec4dd6d3e07c255e63c314dbed5.svg","isPro":false,"fullname":"Marcus kk","user":"marcuskwan","type":"user"},{"_id":"65430ab64539d4807058fb75","avatarUrl":"/avatars/dfb3036508106dcbaa54c46f062c644c.svg","isPro":false,"fullname":"Zhihao Lin","user":"mathieulin","type":"user"},{"_id":"67a94bd5f8b31c37085e0edb","avatarUrl":"/avatars/b332cd9b57015ddbdf33b8645c9a1857.svg","isPro":false,"fullname":"Jiayi Zhang","user":"joyz778877","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.02646.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2607.02646 in a model README.md to link it from this page.

Cite arxiv.org/abs/2607.02646 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2607.02646 in a Space README.md to link it from this page.