{"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/llara-supercharging-robot-learning-data-for","title":"LLaRA: Supercharging Robot Learning Data for Vision-Language Policy","arxiv_id":"2406.20095","date":"2024-06-28","proceeding":null,"authors":["Xiang Li","Cristina Mata","Jongwoo Park","Kumara Kahatapitiya","Yoo Sung Jang","Jinghuan Shang","Kanchana Ranasinghe","Ryan Burgert","Mu Cai","Yong Jae Lee","Michael S. Ryoo"],"abstract":"Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when constrained by a limited number of robot demonstrations. In this work, we introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations and enables an efficient transfer of a pretrained VLM into a powerful VLA, motivated by the success of visual instruction tuning in Computer Vision. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets, aligning robotic actions with image pixel coordinates. Further, we enhance this dataset in a self-supervised manner by defining six auxiliary tasks, without requiring any additional action annotations. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control. Through experiments across multiple simulated and real-world tasks, we demonstrate that LLaRA achieves state-of-the-art performance while preserving the generalization capabilities of large language models. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.","url_abs":"https://arxiv.org/abs/2406.20095v3","url_pdf":"https://arxiv.org/pdf/2406.20095v3.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":"llara-supercharging-robot-learning-data-for","repo_url":"https://github.com/lostxine/llara","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"vision-language-action","task_name":"Vision-Language-Action"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.20095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.20095"}},"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":"deterministic:regex_extraction","url":"https://github.com/LostXine/LLaRA","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lostxine/llara","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":9,"ran_draft_wrong":3,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":15,"ran":13,"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":"ca12919c16b4a4f5","entry":"action_to_text","repo":"LostXine/LLaRA","repo_kind":"official","path":"eval/eval-rt2.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/eval/eval-rt2.py","link_basis":"first_harvest_node","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":"ca12919c16b4a4f5"}},{"code_sha256_prefix":"91dc40b44121e385","entry":"all_gather","repo":"LostXine/LLaRA","repo_kind":"official","path":"maskrcnn/utils.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/maskrcnn/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91dc40b44121e385"}},{"code_sha256_prefix":"20e4f665698a3d18","entry":"collate_fn","repo":"LostXine/LLaRA","repo_kind":"official","path":"train-llava/llava/eval/model_vqa_loader.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/train-llava/llava/eval/model_vqa_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20e4f665698a3d18"}},{"code_sha256_prefix":"0ec4ff97dc3a732e","entry":"collate_fn","repo":"LostXine/LLaRA","repo_kind":"official","path":"maskrcnn/utils.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/maskrcnn/utils.py","link_basis":"first_harvest_node","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":"0ec4ff97dc3a732e"}},{"code_sha256_prefix":"b77412266f910afa","entry":"get_bounding_box","repo":"LostXine/LLaRA","repo_kind":"official","path":"eval/vima_utils.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/eval/vima_utils.py","link_basis":"first_harvest_node","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":"b77412266f910afa"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"LostXine/LLaRA","repo_kind":"official","path":"train-llava/llava/eval/model_vqa.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/train-llava/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"9b3c1cb391672ccb","entry":"load_image","repo":"LostXine/LLaRA","repo_kind":"official","path":"train-llava/predict.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/train-llava/predict.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"code_sha256_prefix":"c072147381d37e39","entry":"pix2pos_front","repo":"LostXine/LLaRA","repo_kind":"official","path":"eval/vima_utils.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/eval/vima_utils.py","link_basis":"first_harvest_node","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":"c072147381d37e39"}},{"code_sha256_prefix":"67c19efa51776cee","entry":"pos2pix_front","repo":"LostXine/LLaRA","repo_kind":"official","path":"eval/vima_utils.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/eval/vima_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67c19efa51776cee"}},{"code_sha256_prefix":"7b583a6159d6539d","entry":"quantize_float_to_text","repo":"LostXine/LLaRA","repo_kind":"official","path":"eval/eval-rt2.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/eval/eval-rt2.py","link_basis":"first_harvest_node","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":"7b583a6159d6539d"}},{"code_sha256_prefix":"d4ff7353113eadb2","entry":"reduce_dict","repo":"LostXine/LLaRA","repo_kind":"official","path":"maskrcnn/utils.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/maskrcnn/utils.py","link_basis":"first_harvest_node","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":"d4ff7353113eadb2"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"LostXine/LLaRA","repo_kind":"official","path":"train-llava/llava/eval/model_vqa.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/train-llava/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"2c1424966e072851","entry":"text_to_float","repo":"LostXine/LLaRA","repo_kind":"official","path":"eval/eval-rt2.py","file_url":"https://github.com/LostXine/LLaRA/blob/HEAD/eval/eval-rt2.py","link_basis":"first_harvest_node","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":"2c1424966e072851"}},{"code_sha256_prefix":"e8b1d3f3b543afbc","entry":"LlavaLlamaForCausalLM","repo":"lostxine/llara","repo_kind":"official","path":"train-llava/llava/model/language_model/llava_llama.py","file_url":"https://github.com/lostxine/llara/blob/HEAD/train-llava/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","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":"e8b1d3f3b543afbc"}},{"code_sha256_prefix":"6106e117d2c9317b","entry":"LlavaMetaForCausalLM","repo":"lostxine/llara","repo_kind":"official","path":"train-llava/llava/model/language_model/llava_llama.py","file_url":"https://github.com/lostxine/llara/blob/HEAD/train-llava/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","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":"6106e117d2c9317b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}