{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/humanvla-towards-vision-language-directed","title":"HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid","arxiv_id":"2406.19972","date":"2024-06-28","proceeding":null,"authors":["Xinyu Xu","Yizheng Zhang","Yong-Lu Li","Lei Han","Cewu Lu"],"abstract":"Physical Human-Scene Interaction (HSI) plays a crucial role in numerous applications. However, existing HSI techniques are limited to specific object dynamics and privileged information, which prevents the development of more comprehensive applications. To address this limitation, we introduce HumanVLA for general object rearrangement directed by practical vision and language. A teacher-student framework is utilized to develop HumanVLA. A state-based teacher policy is trained first using goal-conditioned reinforcement learning and adversarial motion prior. Then, it is distilled into a vision-language-action model via behavior cloning. We propose several key insights to facilitate the large-scale learning process. To support general object rearrangement by physical humanoid, we introduce a novel Human-in-the-Room dataset encompassing various rearrangement tasks. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed approach.","url_abs":"https://arxiv.org/abs/2406.19972v2","url_pdf":"https://arxiv.org/pdf/2406.19972v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"humanvla-towards-vision-language-directed","repo_url":"https://github.com/AllenXuuu/HumanVLA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.19972","atlas_url":"https://app.syntology.ai/?focus=2406.19972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19972"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/mohamedhassanmus/SAMP","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AllenXuuu/HumanVLA","reach":null}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"661a3b9f4cdce825","entry":"BaseNetwork","repo":"AllenXuuu/HumanVLA","repo_kind":"official","path":"models/dagger/vla_network.py","file_url":"https://github.com/AllenXuuu/HumanVLA/blob/HEAD/models/dagger/vla_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"661a3b9f4cdce825"}},{"code_sha256_prefix":"bd2f4055d9632f22","entry":"ResBlock","repo":"AllenXuuu/HumanVLA","repo_kind":"official","path":"models/dagger/vla_network.py","file_url":"https://github.com/AllenXuuu/HumanVLA/blob/HEAD/models/dagger/vla_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd2f4055d9632f22"}},{"code_sha256_prefix":"94e925f5c51f7d0c","entry":"RunningMeanStd","repo":"AllenXuuu/HumanVLA","repo_kind":"official","path":"models/dagger/vla_network.py","file_url":"https://github.com/AllenXuuu/HumanVLA/blob/HEAD/models/dagger/vla_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94e925f5c51f7d0c"}},{"code_sha256_prefix":"494ec3a18baeb896","entry":"VLANetwork","repo":"AllenXuuu/HumanVLA","repo_kind":"official","path":"models/dagger/vla_network.py","file_url":"https://github.com/AllenXuuu/HumanVLA/blob/HEAD/models/dagger/vla_network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"494ec3a18baeb896"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}