{"work":{"id":"3e7e65c5-5aed-4fe9-8414-2092bcb31cc7","openalex_id":null,"doi":null,"arxiv_id":"2406.09246","raw_key":null,"title":"OpenVLA: An Open-Source Vision-Language-Action Model","authors":null,"authors_text":"Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair","year":2024,"venue":"cs.RO","abstract":"Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for adoption. Addressing these challenges, we introduce OpenVLA, a 7B-parameter open-source VLA trained on a diverse collection of 970k real-world robot demonstrations. OpenVLA builds on a Llama 2 language model combined with a visual encoder that fuses pretrained features from DINOv2 and SigLIP. As a product of the added data diversity and new model components, OpenVLA demonstrates strong results for generalist manipulation, outperforming closed models such as RT-2-X (55B) by 16.5% in absolute task success rate across 29 tasks and multiple robot embodiments, with 7x fewer parameters. We further show that we can effectively fine-tune OpenVLA for new settings, with especially strong generalization results in multi-task environments involving multiple objects and strong language grounding abilities, and outperform expressive from-scratch imitation learning methods such as Diffusion Policy by 20.4%. We also explore compute efficiency; as a separate contribution, we show that OpenVLA can be fine-tuned on consumer GPUs via modern low-rank adaptation methods and served efficiently via quantization without a hit to downstream success rate. Finally, we release model checkpoints, fine-tuning notebooks, and our PyTorch codebase with built-in support for training VLAs at scale on Open X-Embodiment datasets.","external_url":"https://arxiv.org/abs/2406.09246","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T08:20:31.776505+00:00","pith_arxiv_id":"2406.09246","created_at":"2026-05-09T05:45:23.357796+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"OpenVLA: An Open-Source Vision-Language-Action Model","render_title":"OpenVLA: An Open-Source Vision-Language-Action Model"},"hub":{"state":{"work_id":"3e7e65c5-5aed-4fe9-8414-2092bcb31cc7","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":319,"external_cited_by_count":null,"distinct_field_count":12,"first_pith_cited_at":"2024-05-23T01:43:54+00:00","last_pith_cited_at":"2026-05-22T17:08:37+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-12T07:29:14.072699+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":93},{"context_role":"baseline","n":20},{"context_role":"method","n":7},{"context_role":"other","n":2}],"polarity_counts":[{"context_polarity":"background","n":88},{"context_polarity":"baseline","n":20},{"context_polarity":"use_method","n":7},{"context_polarity":"unclear","n":6},{"context_polarity":"support","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"OpenVLA: An Open-Source Vision-Language-Action Model","claims":[{"claim_text":"Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for ado","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks OpenVLA: An Open-Source Vision-Language-Action Model because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T21:53:36.669330+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"243ae73b-9e68-445f-b88e-fa0b28f4c914","orcid":null,"display_name":"Moo Jin Kim"},{"id":"9821de6a-6143-4939-8865-7d9c02424af9","orcid":null,"display_name":"Karl Pertsch"},{"id":"9a5d4ee6-e5d5-4afd-89cf-8f80084b69ba","orcid":null,"display_name":"Siddharth Karamcheti"},{"id":"90759b5f-6078-43cb-8cab-d6d90667da4a","orcid":null,"display_name":"Ted Xiao"},{"id":"c277791e-8df4-4262-99f1-6b73bf8a525e","orcid":null,"display_name":"Ashwin Balakrishna"},{"id":"863a3a51-2bb9-4ec3-9cf1-7535b3809d8b","orcid":null,"display_name":"Suraj Nair"}]},"error":null,"updated_at":"2026-05-13T21:53:34.106773+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T21:53:40.277505+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","shared_citers":96},{"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","shared_citers":67},{"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","shared_citers":56},{"title":"Octo: An Open-Source Generalist Robot Policy","work_id":"f9ca0722-8855-48c3-a27a-0eefb7e19253","shared_citers":55},{"title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","work_id":"6fe159e0-fa73-481a-88d4-4719c15140be","shared_citers":44},{"title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","work_id":"04f46bb3-4346-47e8-bf09-c75d91f96e87","shared_citers":43},{"title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","work_id":"e2db69c7-ee8a-4cb7-a761-7b8de1dfcf97","shared_citers":40},{"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","shared_citers":40},{"title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","work_id":"12319725-bc7d-4c32-a229-ad270a7460bc","shared_citers":34},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":32},{"title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","work_id":"83a8f966-6cfa-4f21-81f3-87440aae238f","shared_citers":30},{"title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","work_id":"13253de2-3d89-415c-8c2f-3adb25d4c337","shared_citers":27},{"title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","work_id":"62f0fb6c-e6ae-4dc4-95a4-d9dd64b240e8","shared_citers":27},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":24},{"title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","work_id":"4b158d3e-3dff-4412-85cd-baa879465a5e","shared_citers":23},{"title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","work_id":"843ab5eb-2815-4db8-b3bc-890b23fa5ffa","shared_citers":23},{"title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","work_id":"9b985126-4a2f-4bdf-b014-2a7524ec634e","shared_citers":22},{"title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","work_id":"0c5e9314-5fa7-4613-ad12-605a71d561d2","shared_citers":22},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":21},{"title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","work_id":"62dbe235-8473-4190-8686-17e7437de50f","shared_citers":20},{"title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","work_id":"aebf924c-e761-437e-9cee-f1ccc2e427bd","shared_citers":19},{"title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","work_id":"662203ad-084f-42c4-8e60-977b3173755b","shared_citers":19},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":19},{"title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","work_id":"592041b3-3ca2-4836-8dd4-f8095d8a692b","shared_citers":19}],"time_series":[{"n":5,"year":2024},{"n":9,"year":2025},{"n":142,"year":2026}]},"error":null,"updated_at":"2026-05-13T21:53:36.547740+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"fixed":1,"items":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-13T21:53:42.682854+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"OpenVLA: An Open-Source Vision-Language-Action Model","claims":[{"claim_text":"Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for ado","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks OpenVLA: An Open-Source Vision-Language-Action Model because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T21:53:42.684902+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"OpenVLA: An Open-Source Vision-Language-Action Model","claims":[{"claim_text":"Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for ado","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks OpenVLA: An Open-Source Vision-Language-Action Model because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T21:53:36.671239+00:00"}},"summary":{"title":"OpenVLA: An Open-Source Vision-Language-Action Model","claims":[{"claim_text":"Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for ado","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks OpenVLA: An Open-Source Vision-Language-Action Model because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","shared_citers":96},{"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","shared_citers":67},{"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","shared_citers":56},{"title":"Octo: An Open-Source Generalist Robot Policy","work_id":"f9ca0722-8855-48c3-a27a-0eefb7e19253","shared_citers":55},{"title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","work_id":"6fe159e0-fa73-481a-88d4-4719c15140be","shared_citers":44},{"title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","work_id":"04f46bb3-4346-47e8-bf09-c75d91f96e87","shared_citers":43},{"title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","work_id":"e2db69c7-ee8a-4cb7-a761-7b8de1dfcf97","shared_citers":40},{"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","shared_citers":40},{"title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","work_id":"12319725-bc7d-4c32-a229-ad270a7460bc","shared_citers":34},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":32},{"title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","work_id":"83a8f966-6cfa-4f21-81f3-87440aae238f","shared_citers":30},{"title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","work_id":"13253de2-3d89-415c-8c2f-3adb25d4c337","shared_citers":27},{"title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","work_id":"62f0fb6c-e6ae-4dc4-95a4-d9dd64b240e8","shared_citers":27},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":24},{"title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","work_id":"4b158d3e-3dff-4412-85cd-baa879465a5e","shared_citers":23},{"title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","work_id":"843ab5eb-2815-4db8-b3bc-890b23fa5ffa","shared_citers":23},{"title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","work_id":"9b985126-4a2f-4bdf-b014-2a7524ec634e","shared_citers":22},{"title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","work_id":"0c5e9314-5fa7-4613-ad12-605a71d561d2","shared_citers":22},{"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","shared_citers":21},{"title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","work_id":"62dbe235-8473-4190-8686-17e7437de50f","shared_citers":20},{"title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","work_id":"aebf924c-e761-437e-9cee-f1ccc2e427bd","shared_citers":19},{"title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","work_id":"662203ad-084f-42c4-8e60-977b3173755b","shared_citers":19},{"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","shared_citers":19},{"title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","work_id":"592041b3-3ca2-4836-8dd4-f8095d8a692b","shared_citers":19}],"time_series":[{"n":5,"year":2024},{"n":9,"year":2025},{"n":142,"year":2026}]},"authors":[{"id":"c277791e-8df4-4262-99f1-6b73bf8a525e","orcid":null,"display_name":"Ashwin Balakrishna","source":"manual","import_confidence":0.72},{"id":"9821de6a-6143-4939-8865-7d9c02424af9","orcid":null,"display_name":"Karl Pertsch","source":"manual","import_confidence":0.72},{"id":"243ae73b-9e68-445f-b88e-fa0b28f4c914","orcid":null,"display_name":"Moo Jin Kim","source":"manual","import_confidence":0.72},{"id":"9a5d4ee6-e5d5-4afd-89cf-8f80084b69ba","orcid":null,"display_name":"Siddharth Karamcheti","source":"manual","import_confidence":0.72},{"id":"863a3a51-2bb9-4ec3-9cf1-7535b3809d8b","orcid":null,"display_name":"Suraj Nair","source":"manual","import_confidence":0.72},{"id":"90759b5f-6078-43cb-8cab-d6d90667da4a","orcid":null,"display_name":"Ted Xiao","source":"manual","import_confidence":0.72}]}}