{"id":"93f1639a823c38be6848c6e9cc7db15092043af9df87b8094e1e8ac41699b5a9","title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","argument":"Authors Jiaao Yu, Yanjian Zhang, Haoyang Jiang, Guillaume Wisniewski, Nadi Tomeh and Shijie Jia present TouchéWorld, a framework for adding hand gestures to video world models that users navigate with a camera. They say the model generates video from an initial image and scene-description prompt, conditioned on camera and hand controls aligned over time. To train it, they assemble camera--hand data from egocentric videos, then combine spatial hand-skeleton conditioning with numerical hand-motion features. Causal adaptation and few-step distillation support chunk-level online generation, so users can adjust controls in response to generated visual feedback. The authors also introduce TouchéBench to evaluate whether hand motions are followed, camera and hand controls coordinate, interaction works online, and objects respond. The report frames these components as a way to study continuous exploration and hand-driven interaction in generated environments. The abstract describes the framework and evaluation areas, but does not give benchmark results or establish how well the system performs.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the arXiv abstract, which describes the framework and evaluation areas but provides no TouchéBench results. The abstract does not establish how well generated interactions work beyond describing the intended evaluation areas. The full report is not included in the supplied evidence.","speaker":{"name":"Yu, Jiaao, Zhang, Yanjian, Jiang, Haoyang, Wisniewski, Guillaume, Tomeh, Nadi, Jia, Shijie","roleAtSource":"Article author"},"source":{"title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.06061","publishedAt":"2026-11-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors present TouchéWorld as a framework combining gesture-driven interaction with a camera-controlled video world model.","excerpt":"We present TouchéWorld, a framework that integrates gesture-driven interaction into a camera-controlled video world model.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The framework generates video from an initial image and scene-description prompt, conditioned on temporally aligned camera and hand controls.","excerpt":"the model generates video conditioned on temporally aligned camera and hand controls.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The authors construct joint camera--hand training data from heterogeneous egocentric videos using annotation completion, consistency-based filtering and temporal alignment.","excerpt":"We construct joint camera--hand training data from heterogeneous egocentric videos through annotation completion, consistency-based filtering, and temporal alignment.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The authors say causal adaptation and few-step distillation support chunk-level online generation, allowing users to change controls in response to generated visual feedback.","excerpt":"Causal adaptation and few-step distillation support chunk-level online generation, allowing users to update their controls based on generated visual feedback.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"TouchéBench is introduced to evaluate hand-motion following, camera--hand coordination, online interaction and object response.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The abstract does not report TouchéWorld's performance on the evaluations it describes.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","url":"https://arxiv.org/abs/2611.06061","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06061","checkedAt":"2026-11-10T17:26:06.623Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How does TouchéWorld perform on the hand-motion following, camera--hand coordination, online interaction and object-response evaluations in TouchéBench?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","summary":"Authors Jiaao Yu, Yanjian Zhang, Haoyang Jiang, Guillaume Wisniewski, Nadi Tomeh and Shijie Jia present TouchéWorld, a framework for adding hand gestures to video world models that users navigate with a camera. They say the model generates video from an initial image and scene-description prompt, conditioned on camera and hand controls aligned over time. To train it, they assemble camera--hand data from egocentric videos, then combine spatial hand-skeleton conditioning with numerical hand-motion features. Causal adaptation and few-step distillation support chunk-level online generation, so users can adjust controls in response to generated visual feedback. The authors also introduce TouchéBench to evaluate whether hand motions are followed, camera and hand controls coordinate, interaction works online, and objects respond. The report frames these components as a way to study continuous exploration and hand-driven interaction in generated environments. The abstract describes the framework and evaluation areas, but does not give benchmark results or establish how well the system performs.","question":"How does TouchéWorld perform on the hand-motion following, camera--hand coordination, online interaction and object-response evaluations in TouchéBench?","claims":[{"text":"The authors present TouchéWorld as a framework combining gesture-driven interaction with a camera-controlled video world model.","excerpt":"We present TouchéWorld, a framework that integrates gesture-driven interaction into a camera-controlled video world model.","support":"source-stated"},{"text":"The framework generates video from an initial image and scene-description prompt, conditioned on temporally aligned camera and hand controls.","excerpt":"the model generates video conditioned on temporally aligned camera and hand controls.","support":"source-stated"},{"text":"The authors construct joint camera--hand training data from heterogeneous egocentric videos using annotation completion, consistency-based filtering and temporal alignment.","excerpt":"We construct joint camera--hand training data from heterogeneous egocentric videos through annotation completion, consistency-based filtering, and temporal alignment.","support":"source-stated"},{"text":"The authors say causal adaptation and few-step distillation support chunk-level online generation, allowing users to change controls in response to generated visual feedback.","excerpt":"Causal adaptation and few-step distillation support chunk-level online generation, allowing users to update their controls based on generated visual feedback.","support":"source-stated"},{"text":"TouchéBench is introduced to evaluate hand-motion following, camera--hand coordination, online interaction and object response.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","support":"source-stated"},{"text":"The abstract does not report TouchéWorld's performance on the evaluations it describes.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","support":"interpretation"}],"limitations":["The supplied evidence is the arXiv abstract, which describes the framework and evaluation areas but provides no TouchéBench results.","The abstract does not establish how well generated interactions work beyond describing the intended evaluation areas. The full report is not included in the supplied evidence."],"mediaId":"bbc454412f3d76f865703cac0f21661397945e1a05ab75a0ee0d119f790ab354","correctionReason":null,"id":"93f1639a823c38be6848c6e9cc7db15092043af9df87b8094e1e8ac41699b5a9","publicationId":"bbd7d316-c837-482c-8b26-9c86d5877322","version":1,"sourceUrl":"https://arxiv.org/abs/2611.06061","sourceTitle":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:24.065Z","createdAt":"2026-11-10T00:23:05.263Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"bbc454412f3d76f865703cac0f21661397945e1a05ab75a0ee0d119f790ab354","kind":"article","url":"https://arxiv.org/abs/2611.06061","sourceUrl":"https://arxiv.org/abs/2611.06061","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T00:18:21.173Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06061","checkedAt":"2026-11-10T17:26:06.623Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"bbc454412f3d76f865703cac0f21661397945e1a05ab75a0ee0d119f790ab354","confidence":0.86,"provider":"typesafe","model":"jev-1.13.0","inputHash":"03de483382d35be353db299f9cd1fd7c16ae048bffd158512247b3b77d63582d","decidedAt":"2026-11-10T00:18:22.270Z"},"provenance":{"textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observationId":"705d7693ea5f4c9aeb16ba0b7419ab2b86f87c974abf316b940df6212f6c57a7","retrievedAt":"2026-11-10T00:18:20.999Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"a4d2c296-8cd0-4c69-8355-ae15a03ce9da"},"reviewer":{"model":"gpt-6-luna","runId":"d24b16a3-64bd-494b-8e43-c7ed787fda0f"}},"audit":{"status":"passed","reviewedAt":"2026-11-10T00:23:05.263Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Yu, Jiaao","url":null,"kind":"unknown"},{"name":"Zhang, Yanjian","url":null,"kind":"unknown"},{"name":"Jiang, Haoyang","url":null,"kind":"unknown"},{"name":"Wisniewski, Guillaume","url":null,"kind":"unknown"},{"name":"Tomeh, Nadi","url":null,"kind":"unknown"},{"name":"Jia, Shijie","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Yu, Jiaao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Yu, Jiaao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Zhang, Yanjian","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Yanjian","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Jiang, Haoyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jiang, Haoyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Wisniewski, Guillaume","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wisniewski, Guillaume","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Tomeh, Nadi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Tomeh, Nadi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Jia, Shijie","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jia, Shijie","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}}],"participationCoverage":{"total":6,"returned":6,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.06061","snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z","basis":"publisher-page-metadata","sourceLinks":45,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/93f1639a823c38be6848c6e9cc7db15092043af9df87b8094e1e8ac41699b5a9/source"}},"canonicalUrl":"https://escapemeridian.com/readings/toucheworld-tech-report-towards-online-unified-camera-hand-93f1639a","formats":{"html":"/readings/toucheworld-tech-report-towards-online-unified-camera-hand-93f1639a","markdown":"/readings/toucheworld-tech-report-towards-online-unified-camera-hand-93f1639a.md","json":"/readings/toucheworld-tech-report-towards-online-unified-camera-hand-93f1639a.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-world-model","name":"World model","explanation":"An AI system's internal model of how an environment behaves, used to predict what happens next or to plan.","referenceUrl":"https://arxiv.org/abs/1803.10122"},{"id":"term-benchmark","name":"Benchmark","explanation":"A defined set of tests used to compare systems. Results depend on the tasks and measures selected.","referenceUrl":"https://arxiv.org/abs/2211.09110"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"},{"id":"time","name":"TIME","kind":"organization","context":"TIME is a news magazine publishing reporting on world affairs, business, technology and the workers behind digital services.","referenceUrls":["https://time.com/"],"path":"/entities/time","json":"/entities/time.json","markdown":"/entities/time.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"93f1639a823c38be6848c6e9cc7db15092043af9df87b8094e1e8ac41699b5a9","revision":"bbd7d316-c837-482c-8b26-9c86d5877322","revisionKind":"publication-id","title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","url":"https://escapemeridian.com/readings/toucheworld-tech-report-towards-online-unified-camera-hand-93f1639a"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.06061","revision":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","revisionKind":"sha256-source-text","title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","url":"https://arxiv.org/abs/2611.06061"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"93f1639a823c38be6848c6e9cc7db15092043af9df87b8094e1e8ac41699b5a9","title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","argument":"Authors Jiaao Yu, Yanjian Zhang, Haoyang Jiang, Guillaume Wisniewski, Nadi Tomeh and Shijie Jia present TouchéWorld, a framework for adding hand gestures to video world models that users navigate with a camera. They say the model generates video from an initial image and scene-description prompt, conditioned on camera and hand controls aligned over time. To train it, they assemble camera--hand data from egocentric videos, then combine spatial hand-skeleton conditioning with numerical hand-motion features. Causal adaptation and few-step distillation support chunk-level online generation, so users can adjust controls in response to generated visual feedback. The authors also introduce TouchéBench to evaluate whether hand motions are followed, camera and hand controls coordinate, interaction works online, and objects respond. The report frames these components as a way to study continuous exploration and hand-driven interaction in generated environments. The abstract describes the framework and evaluation areas, but does not give benchmark results or establish how well the system performs.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the arXiv abstract, which describes the framework and evaluation areas but provides no TouchéBench results. The abstract does not establish how well generated interactions work beyond describing the intended evaluation areas. The full report is not included in the supplied evidence.","speaker":{"name":"Yu, Jiaao, Zhang, Yanjian, Jiang, Haoyang, Wisniewski, Guillaume, Tomeh, Nadi, Jia, Shijie","roleAtSource":"Article author"},"source":{"title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.06061","publishedAt":"2026-11-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors present TouchéWorld as a framework combining gesture-driven interaction with a camera-controlled video world model.","excerpt":"We present TouchéWorld, a framework that integrates gesture-driven interaction into a camera-controlled video world model.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The framework generates video from an initial image and scene-description prompt, conditioned on temporally aligned camera and hand controls.","excerpt":"the model generates video conditioned on temporally aligned camera and hand controls.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The authors construct joint camera--hand training data from heterogeneous egocentric videos using annotation completion, consistency-based filtering and temporal alignment.","excerpt":"We construct joint camera--hand training data from heterogeneous egocentric videos through annotation completion, consistency-based filtering, and temporal alignment.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The authors say causal adaptation and few-step distillation support chunk-level online generation, allowing users to change controls in response to generated visual feedback.","excerpt":"Causal adaptation and few-step distillation support chunk-level online generation, allowing users to update their controls based on generated visual feedback.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"TouchéBench is introduced to evaluate hand-motion following, camera--hand coordination, online interaction and object response.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","url":"https://arxiv.org/abs/2611.06061","relationship":"Source-stated"},{"text":"The abstract does not report TouchéWorld's performance on the evaluations it describes.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","url":"https://arxiv.org/abs/2611.06061","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06061","checkedAt":"2026-11-10T17:26:06.623Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How does TouchéWorld perform on the hand-motion following, camera--hand coordination, online interaction and object-response evaluations in TouchéBench?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","summary":"Authors Jiaao Yu, Yanjian Zhang, Haoyang Jiang, Guillaume Wisniewski, Nadi Tomeh and Shijie Jia present TouchéWorld, a framework for adding hand gestures to video world models that users navigate with a camera. They say the model generates video from an initial image and scene-description prompt, conditioned on camera and hand controls aligned over time. To train it, they assemble camera--hand data from egocentric videos, then combine spatial hand-skeleton conditioning with numerical hand-motion features. Causal adaptation and few-step distillation support chunk-level online generation, so users can adjust controls in response to generated visual feedback. The authors also introduce TouchéBench to evaluate whether hand motions are followed, camera and hand controls coordinate, interaction works online, and objects respond. The report frames these components as a way to study continuous exploration and hand-driven interaction in generated environments. The abstract describes the framework and evaluation areas, but does not give benchmark results or establish how well the system performs.","question":"How does TouchéWorld perform on the hand-motion following, camera--hand coordination, online interaction and object-response evaluations in TouchéBench?","claims":[{"text":"The authors present TouchéWorld as a framework combining gesture-driven interaction with a camera-controlled video world model.","excerpt":"We present TouchéWorld, a framework that integrates gesture-driven interaction into a camera-controlled video world model.","support":"source-stated"},{"text":"The framework generates video from an initial image and scene-description prompt, conditioned on temporally aligned camera and hand controls.","excerpt":"the model generates video conditioned on temporally aligned camera and hand controls.","support":"source-stated"},{"text":"The authors construct joint camera--hand training data from heterogeneous egocentric videos using annotation completion, consistency-based filtering and temporal alignment.","excerpt":"We construct joint camera--hand training data from heterogeneous egocentric videos through annotation completion, consistency-based filtering, and temporal alignment.","support":"source-stated"},{"text":"The authors say causal adaptation and few-step distillation support chunk-level online generation, allowing users to change controls in response to generated visual feedback.","excerpt":"Causal adaptation and few-step distillation support chunk-level online generation, allowing users to update their controls based on generated visual feedback.","support":"source-stated"},{"text":"TouchéBench is introduced to evaluate hand-motion following, camera--hand coordination, online interaction and object response.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","support":"source-stated"},{"text":"The abstract does not report TouchéWorld's performance on the evaluations it describes.","excerpt":"We further introduce TouchéBench to evaluate hand-motion following, camera--hand coordination, online interaction, and object response.","support":"interpretation"}],"limitations":["The supplied evidence is the arXiv abstract, which describes the framework and evaluation areas but provides no TouchéBench results.","The abstract does not establish how well generated interactions work beyond describing the intended evaluation areas. The full report is not included in the supplied evidence."],"mediaId":"bbc454412f3d76f865703cac0f21661397945e1a05ab75a0ee0d119f790ab354","correctionReason":null,"id":"93f1639a823c38be6848c6e9cc7db15092043af9df87b8094e1e8ac41699b5a9","publicationId":"bbd7d316-c837-482c-8b26-9c86d5877322","version":1,"sourceUrl":"https://arxiv.org/abs/2611.06061","sourceTitle":"TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:24.065Z","createdAt":"2026-11-10T00:23:05.263Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"bbc454412f3d76f865703cac0f21661397945e1a05ab75a0ee0d119f790ab354","kind":"article","url":"https://arxiv.org/abs/2611.06061","sourceUrl":"https://arxiv.org/abs/2611.06061","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T00:18:21.173Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06061","checkedAt":"2026-11-10T17:26:06.623Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"bbc454412f3d76f865703cac0f21661397945e1a05ab75a0ee0d119f790ab354","confidence":0.86,"provider":"typesafe","model":"jev-1.13.0","inputHash":"03de483382d35be353db299f9cd1fd7c16ae048bffd158512247b3b77d63582d","decidedAt":"2026-11-10T00:18:22.270Z"},"provenance":{"textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observationId":"705d7693ea5f4c9aeb16ba0b7419ab2b86f87c974abf316b940df6212f6c57a7","retrievedAt":"2026-11-10T00:18:20.999Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"a4d2c296-8cd0-4c69-8355-ae15a03ce9da"},"reviewer":{"model":"gpt-6-luna","runId":"d24b16a3-64bd-494b-8e43-c7ed787fda0f"}},"audit":{"status":"passed","reviewedAt":"2026-11-10T00:23:05.263Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Yu, Jiaao","url":null,"kind":"unknown"},{"name":"Zhang, Yanjian","url":null,"kind":"unknown"},{"name":"Jiang, Haoyang","url":null,"kind":"unknown"},{"name":"Wisniewski, Guillaume","url":null,"kind":"unknown"},{"name":"Tomeh, Nadi","url":null,"kind":"unknown"},{"name":"Jia, Shijie","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Yu, Jiaao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Yu, Jiaao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Zhang, Yanjian","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Yanjian","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Jiang, Haoyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jiang, Haoyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Wisniewski, Guillaume","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wisniewski, Guillaume","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Tomeh, Nadi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Tomeh, Nadi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}},{"actor":{"name":"Jia, Shijie","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jia, Shijie","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06061","locator":"head/meta[name=author|citation_author]"},"assertionId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T17:26:06.623Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","sourceUrl":"https://arxiv.org/abs/2611.06061","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z"}}],"participationCoverage":{"total":6,"returned":6,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.06061","snapshotId":"7f470d4a37bd3f95a0d826905ce3e5f6b7fa5e8bb11ffda72df02da7de3f3150","contentSha256":"0ef9168c76154e2f8f3617f0e50f7d114f526bf84dabf6e35b59216bed521f6e","textHash":"a83efa781e80620213d07138a587ec921f15736d112cae148949a55c185cdc9f","observedAt":"2026-11-10T17:26:06.623Z","basis":"publisher-page-metadata","sourceLinks":45,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/93f1639a823c38be6848c6e9cc7db15092043af9df87b8094e1e8ac41699b5a9/source"}}}],"audits":[{"publicationId":"bbd7d316-c837-482c-8b26-9c86d5877322","verdict":"passed","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading names all six listed authors and attributes the framework, data construction, online generation and TouchéBench to them, using 'They say' and 'The authors' framing. It does not present source claims as established fact.","excerpt":"Authors:Jiaao Yu, Yanjian Zhang, Haoyang Jiang, Guillaume Wisniewski, Nadi Tomeh, Shijie Jia"},{"dimension":"summary","status":"pass","explanation":"The reading follows the abstract's structure: the framework, inputs and controls, training data, adaptation, online generation, benchmark, and framing. It explains the practical result of the online generation: users can adjust controls in response to generated video. Terms such as video world model, egocentric videos and few-step distillation are kept exactly, consistent with tooltip handling. The question asks about the gap the abstract leaves open, missing benchmark results, rather than making a leading claim. The source's modest framing as a framework for study is preserved, without hype.","excerpt":"Together, these components establish a framework for studying continuous exploration and hand-driven interaction within generative worlds."},{"dimension":"date","status":"pass","explanation":"The originalPublished date of 2026-11-04 matches the arXiv v1 submission date. The feed date of Nov 5 is later and is correctly not used.","excerpt":"[Submitted on 4 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"Each source-stated claim matches an abstract sentence verbatim. The interpretation claim that the abstract reports no performance results is accurate, because the abstract only lists evaluation areas. The reading implies no benefits, costs or reliability beyond the source, and its limitations correctly note that the full report is not included.","excerpt":"Causal adaptation and few-step distillation support chunk-level online generation, allowing users to update their controls based on generated visual feedback."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct arXiv abstract page for this paper, matching the source URL. No better source media was found.","excerpt":null}],"createdAt":"2026-11-10T00:23:05.263Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}