{"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/fine-tuning-vision-language-action-models","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","arxiv_id":"2502.19645","date":"2025-02-27","proceeding":null,"authors":["Moo Jin Kim","Chelsea Finn","Percy Liang"],"abstract":"Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. Despite these successes, VLAs struggle with novel robot setups and require fine-tuning to achieve good performance, yet how to most effectively fine-tune them is unclear given many possible strategies. In this work, we study key VLA adaptation design choices such as different action decoding schemes, action representations, and learning objectives for fine-tuning, using OpenVLA as our representative base model. Our empirical analysis informs an Optimized Fine-Tuning (OFT) recipe that integrates parallel decoding, action chunking, a continuous action representation, and a simple L1 regression-based learning objective to altogether improve inference efficiency, policy performance, and flexibility in the model's input-output specifications. We propose OpenVLA-OFT, an instantiation of this recipe, which sets a new state of the art on the LIBERO simulation benchmark, significantly boosting OpenVLA's average success rate across four task suites from 76.5% to 97.1% while increasing action generation throughput by 26$\\times$. In real-world evaluations, our fine-tuning recipe enables OpenVLA to successfully execute dexterous, high-frequency control tasks on a bimanual ALOHA robot and outperform other VLAs ($\\pi_0$ and RDT-1B) fine-tuned using their default recipes, as well as strong imitation learning policies trained from scratch (Diffusion Policy and ACT) by up to 15% (absolute) in average success rate. We release code for OFT and pretrained model checkpoints at https://openvla-oft.github.io/.","url_abs":"https://arxiv.org/abs/2502.19645v2","url_pdf":"https://arxiv.org/pdf/2502.19645v2.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":"fine-tuning-vision-language-action-models","repo_url":"https://github.com/moojink/openvla-oft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"vision-language-action","task_name":"Vision-Language-Action"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.19645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19645"}},"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/moojink/openvla-oft","reach":null}],"summary":{"ran_draft_wrong":4},"by_repo_kind":{"listed":{"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":"8b2a2aa060e1e24f","entry":"get_run_id","repo":"moojink/openvla-oft","repo_kind":"listed","path":"vla-scripts/finetune.py","file_url":"https://github.com/moojink/openvla-oft/blob/HEAD/vla-scripts/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b2a2aa060e1e24f"}},{"code_sha256_prefix":"8c56534935f5a294","entry":"load_checkpoint","repo":"moojink/openvla-oft","repo_kind":"listed","path":"vla-scripts/finetune.py","file_url":"https://github.com/moojink/openvla-oft/blob/HEAD/vla-scripts/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c56534935f5a294"}},{"code_sha256_prefix":"99b7442f72fa092c","entry":"load_initial_states","repo":"moojink/openvla-oft","repo_kind":"listed","path":"experiments/robot/libero/run_libero_eval.py","file_url":"https://github.com/moojink/openvla-oft/blob/HEAD/experiments/robot/libero/run_libero_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99b7442f72fa092c"}},{"code_sha256_prefix":"c61f2447224a1296","entry":"remove_ddp_in_checkpoint","repo":"moojink/openvla-oft","repo_kind":"listed","path":"vla-scripts/finetune.py","file_url":"https://github.com/moojink/openvla-oft/blob/HEAD/vla-scripts/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c61f2447224a1296"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}