{"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/vima-general-robot-manipulation-with","title":"VIMA: General Robot Manipulation with Multimodal Prompts","arxiv_id":"2210.03094","date":"2022-10-06","proceeding":null,"authors":["Yunfan Jiang","Agrim Gupta","Zichen Zhang","Guanzhi Wang","Yongqiang Dou","Yanjun Chen","Li Fei-Fei","Anima Anandkumar","Yuke Zhu","Linxi Fan"],"abstract":"Prompt-based learning has emerged as a successful paradigm in natural language processing, where a single general-purpose language model can be instructed to perform any task specified by input prompts. Yet task specification in robotics comes in various forms, such as imitating one-shot demonstrations, following language instructions, and reaching visual goals. They are often considered different tasks and tackled by specialized models. We show that a wide spectrum of robot manipulation tasks can be expressed with multimodal prompts, interleaving textual and visual tokens. Accordingly, we develop a new simulation benchmark that consists of thousands of procedurally-generated tabletop tasks with multimodal prompts, 600K+ expert trajectories for imitation learning, and a four-level evaluation protocol for systematic generalization. We design a transformer-based robot agent, VIMA, that processes these prompts and outputs motor actions autoregressively. VIMA features a recipe that achieves strong model scalability and data efficiency. It outperforms alternative designs in the hardest zero-shot generalization setting by up to $2.9\\times$ task success rate given the same training data. With $10\\times$ less training data, VIMA still performs $2.7\\times$ better than the best competing variant. Code and video demos are available at https://vimalabs.github.io/","url_abs":"https://arxiv.org/abs/2210.03094v2","url_pdf":"https://arxiv.org/pdf/2210.03094v2.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":"abstracts"},"code_links":[{"paper_slug":"vima-general-robot-manipulation-with","repo_url":"https://github.com/vimalabs/VIMABench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vima-general-robot-manipulation-with","repo_url":"https://github.com/vimalabs/VIMA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"systematic-generalization","task_name":"Systematic Generalization"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03094"}},"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/vimalabs/VIMABench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vimalabs/VIMA","reach":null}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1},"listed":{"samples":1,"ran":0,"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":"b538033d270af6cc","entry":"VIMAPolicy","repo":"vimalabs/VIMA","repo_kind":"listed","path":"vima/policy/vima_policy.py","file_url":"https://github.com/vimalabs/VIMA/blob/HEAD/vima/policy/vima_policy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b538033d270af6cc"}},{"code_sha256_prefix":"8ee42dce75ebc151","entry":"f_expand","repo":"vimalabs/VIMABench","repo_kind":"official","path":"vima_bench/utils/utils.py","file_url":"https://github.com/vimalabs/VIMABench/blob/HEAD/vima_bench/utils/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ee42dce75ebc151"}},{"code_sha256_prefix":"7005407d180f27aa","entry":"fast_map_structure","repo":"vimalabs/VIMABench","repo_kind":"official","path":"vima_bench/utils/utils.py","file_url":"https://github.com/vimalabs/VIMABench/blob/HEAD/vima_bench/utils/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7005407d180f27aa"}},{"code_sha256_prefix":"dd0a33da55a387fb","entry":"fill_template","repo":"vimalabs/VIMABench","repo_kind":"official","path":"vima_bench/tasks/utils/pybullet_utils.py","file_url":"https://github.com/vimalabs/VIMABench/blob/HEAD/vima_bench/tasks/utils/pybullet_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd0a33da55a387fb"}},{"code_sha256_prefix":"8e742e65d6f52393","entry":"get_heightmap","repo":"vimalabs/VIMABench","repo_kind":"official","path":"vima_bench/tasks/utils/misc_utils.py","file_url":"https://github.com/vimalabs/VIMABench/blob/HEAD/vima_bench/tasks/utils/misc_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e742e65d6f52393"}},{"code_sha256_prefix":"99d5a31bb646753c","entry":"get_pointcloud","repo":"vimalabs/VIMABench","repo_kind":"official","path":"vima_bench/tasks/utils/misc_utils.py","file_url":"https://github.com/vimalabs/VIMABench/blob/HEAD/vima_bench/tasks/utils/misc_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99d5a31bb646753c"}},{"code_sha256_prefix":"9f16ada880b7515b","entry":"stack_sequence_fields","repo":"vimalabs/VIMABench","repo_kind":"official","path":"vima_bench/utils/utils.py","file_url":"https://github.com/vimalabs/VIMABench/blob/HEAD/vima_bench/utils/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f16ada880b7515b"}},{"code_sha256_prefix":"03ef9899c31d2fc0","entry":"transform_pointcloud","repo":"vimalabs/VIMABench","repo_kind":"official","path":"vima_bench/tasks/utils/misc_utils.py","file_url":"https://github.com/vimalabs/VIMABench/blob/HEAD/vima_bench/tasks/utils/misc_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03ef9899c31d2fc0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}