{"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/univla-learning-to-act-anywhere-with-task","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","arxiv_id":"2505.06111","date":"2025-05-09","proceeding":null,"authors":["Qingwen Bu","Yanting Yang","Jisong Cai","Shenyuan Gao","Guanghui Ren","Maoqing Yao","Ping Luo","Hongyang Li"],"abstract":"A generalist robot should perform effectively across various environments. However, most existing approaches heavily rely on scaling action-annotated data to enhance their capabilities. Consequently, they are often limited to single physical specification and struggle to learn transferable knowledge across different embodiments and environments. To confront these limitations, we propose UniVLA, a new framework for learning cross-embodiment vision-language-action (VLA) policies. Our key innovation is to derive task-centric action representations from videos with a latent action model. This enables us to exploit extensive data across a wide spectrum of embodiments and perspectives. To mitigate the effect of task-irrelevant dynamics, we incorporate language instructions and establish a latent action model within the DINO feature space. Learned from internet-scale videos, the generalist policy can be deployed to various robots through efficient latent action decoding. We obtain state-of-the-art results across multiple manipulation and navigation benchmarks, as well as real-robot deployments. UniVLA achieves superior performance over OpenVLA with less than 1/20 of pretraining compute and 1/10 of downstream data. Continuous performance improvements are observed as heterogeneous data, even including human videos, are incorporated into the training pipeline. The results underscore UniVLA's potential to facilitate scalable and efficient robot policy learning.","url_abs":"https://arxiv.org/abs/2505.06111v2","url_pdf":"https://arxiv.org/pdf/2505.06111v2.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":"univla-learning-to-act-anywhere-with-task","repo_url":"https://github.com/opendrivelab/univla","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"vision-language-action","task_name":"Vision-Language-Action"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dino","method_name":"DINO"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/robot-manipulation-on-calvin","task":"Robot Manipulation","dataset":"CALVIN","model":"UniVLA","rank_in_archive_order":9,"of":19,"metrics":{"avg. sequence length (D to D)":"3.80"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.06111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.06111"}},"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/opendrivelab/univla","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"d4883358a40b04e4","entry":"crop_and_resize","repo":"opendrivelab/univla","repo_kind":"official","path":"experiments/robot/simpler-bridge/policies/univla/univla_model.py","file_url":"https://github.com/opendrivelab/univla/blob/HEAD/experiments/robot/simpler-bridge/policies/univla/univla_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4883358a40b04e4"}},{"code_sha256_prefix":"41c95837c9e5064f","entry":"default","repo":"opendrivelab/univla","repo_kind":"official","path":"latent_action_model/genie/dataset.py","file_url":"https://github.com/opendrivelab/univla/blob/HEAD/latent_action_model/genie/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"41c95837c9e5064f"}},{"code_sha256_prefix":"47688b9e2d2cf299","entry":"exists","repo":"opendrivelab/univla","repo_kind":"official","path":"latent_action_model/genie/dataset.py","file_url":"https://github.com/opendrivelab/univla/blob/HEAD/latent_action_model/genie/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"47688b9e2d2cf299"}},{"code_sha256_prefix":"fb72bc624ec91f13","entry":"get_processor","repo":"opendrivelab/univla","repo_kind":"official","path":"experiments/robot/simpler-bridge/policies/univla/univla_model.py","file_url":"https://github.com/opendrivelab/univla/blob/HEAD/experiments/robot/simpler-bridge/policies/univla/univla_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb72bc624ec91f13"}},{"code_sha256_prefix":"7af07bf1a8a753fe","entry":"remap_state_dicts_for_hf","repo":"opendrivelab/univla","repo_kind":"official","path":"vla-scripts/extern/convert_univla_weights_to_hf.py","file_url":"https://github.com/opendrivelab/univla/blob/HEAD/vla-scripts/extern/convert_univla_weights_to_hf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7af07bf1a8a753fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}