{"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/scaling-up-and-distilling-down-language","title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","arxiv_id":"2307.14535","date":"2023-07-26","proceeding":null,"authors":["Huy Ha","Pete Florence","Shuran Song"],"abstract":"We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy. For (1), we use a large language model (LLM) to guide high-level planning, and sampling-based robot planners (e.g. motion or grasp samplers) for generating diverse and rich manipulation trajectories. To robustify this data-collection process, the LLM also infers a code-snippet for the success condition of each task, simultaneously enabling the data-collection process to detect failure and retry as well as the automatic labeling of trajectories with success/failure. For (2), we extend the diffusion policy single-task behavior-cloning approach to multi-task settings with language conditioning. Finally, we propose a new multi-task benchmark with 18 tasks across five domains to test long-horizon behavior, common-sense reasoning, tool-use, and intuitive physics. We find that our distilled policy successfully learned the robust retrying behavior in its data collection procedure, while improving absolute success rates by 33.2% on average across five domains. Code, data, and additional qualitative results are available on https://www.cs.columbia.edu/~huy/scalingup/.","url_abs":"https://arxiv.org/abs/2307.14535v2","url_pdf":"https://arxiv.org/pdf/2307.14535v2.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":"scaling-up-and-distilling-down-language","repo_url":"https://github.com/real-stanford/scalingup","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.14535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14535"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/real-stanford/scalingup","reach":{"status":"ok"}}],"summary":{"ran":9,"ran_honours":1},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":10,"samples":[{"code_sha256_prefix":"f14e86248656890d","entry":"conv3d","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/unet3d.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/unet3d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f14e86248656890d"}},{"code_sha256_prefix":"23123534570bbc23","entry":"create_conv","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/unet3d.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/unet3d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23123534570bbc23"}},{"code_sha256_prefix":"cb35e06cffb77cfc","entry":"get_view_frustum","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/tsdf.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/tsdf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb35e06cffb77cfc"}},{"code_sha256_prefix":"432a763e2bd52224","entry":"number_of_features_per_level","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/unet3d.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/unet3d.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"432a763e2bd52224"}},{"code_sha256_prefix":"f102ff2f61038681","entry":"plot_to_png","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/utils/core.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/utils/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f102ff2f61038681"}},{"code_sha256_prefix":"9ae9ff9d07e85e77","entry":"replace_bn_with_gn","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/utils.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ae9ff9d07e85e77"}},{"code_sha256_prefix":"d352995c4d862386","entry":"replace_submodules","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/utils.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d352995c4d862386"}},{"code_sha256_prefix":"dc7f3e9cf45d3d8b","entry":"rigid_transform","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/tsdf.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/tsdf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc7f3e9cf45d3d8b"}},{"code_sha256_prefix":"eaba61ec9244ba3a","entry":"rnn_args_from_config","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/algo/robomimic_nets.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/algo/robomimic_nets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eaba61ec9244ba3a"}},{"code_sha256_prefix":"29a6b9b2f3796d51","entry":"split_state_phrase","repo":"real-stanford/scalingup","repo_kind":"official","path":"scalingup/utils/core.py","file_url":"https://github.com/real-stanford/scalingup/blob/HEAD/scalingup/utils/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29a6b9b2f3796d51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}