{"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/manipvqa-injecting-robotic-affordance-and","title":"ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models","arxiv_id":"2403.11289","date":"2024-03-17","proceeding":null,"authors":["Siyuan Huang","Iaroslav Ponomarenko","Zhengkai Jiang","Xiaoqi Li","Xiaobin Hu","Peng Gao","Hongsheng Li","Hao Dong"],"abstract":"While the integration of Multi-modal Large Language Models (MLLMs) with robotic systems has significantly improved robots' ability to understand and execute natural language instructions, their performance in manipulation tasks remains limited due to a lack of robotics-specific knowledge. Conventional MLLMs are typically trained on generic image-text pairs, leaving them deficient in understanding affordances and physical concepts crucial for manipulation. To address this gap, we propose ManipVQA, a novel framework that infuses MLLMs with manipulation-centric knowledge through a Visual Question-Answering (VQA) format. This approach encompasses tool detection, affordance recognition, and a broader understanding of physical concepts. We curated a diverse dataset of images depicting interactive objects, to challenge robotic understanding in tool detection, affordance prediction, and physical concept comprehension. To effectively integrate this robotics-specific knowledge with the inherent vision-reasoning capabilities of MLLMs, we leverage a unified VQA format and devise a fine-tuning strategy. This strategy preserves the original vision-reasoning abilities while incorporating the newly acquired robotic insights. Empirical evaluations conducted in robotic simulators and across various vision task benchmarks demonstrate the robust performance of ManipVQA. The code and dataset are publicly available at https://github.com/SiyuanHuang95/ManipVQA.","url_abs":"https://arxiv.org/abs/2403.11289v2","url_pdf":"https://arxiv.org/pdf/2403.11289v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"manipvqa-injecting-robotic-affordance-and","repo_url":"https://github.com/siyuanhuang95/manipvqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.11289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11289"}},"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/siyuanhuang95/manipvqa","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":8,"samples":[{"code_sha256_prefix":"1cbb43c0dc4ea2ca","entry":"T_padded_resize","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"accessory/eval_manip.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/accessory/eval_manip.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1cbb43c0dc4ea2ca"}},{"code_sha256_prefix":"5887c86feaa968f6","entry":"bb_intersection_over_union","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"accessory/get_ap_tool.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/accessory/get_ap_tool.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5887c86feaa968f6"}},{"code_sha256_prefix":"583539928cd10b3c","entry":"collate_fn","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"accessory/eval_manip.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/accessory/eval_manip.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"583539928cd10b3c"}},{"code_sha256_prefix":"c40d295f8be78649","entry":"extract_bounding_box","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"accessory/get_ap_tool.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/accessory/get_ap_tool.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c40d295f8be78649"}},{"code_sha256_prefix":"cfdf6b9fc39c9664","entry":"format_bounding_box","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"accessory/get_ap_tool.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/accessory/get_ap_tool.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cfdf6b9fc39c9664"}},{"code_sha256_prefix":"877b4942dbab7ce4","entry":"get_json_file_list","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"dataset/dataset_utils.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/dataset/dataset_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"877b4942dbab7ce4"}},{"code_sha256_prefix":"f4e43fb4d725358d","entry":"normalize_number","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"accessory/eval_manip.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/accessory/eval_manip.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f4e43fb4d725358d"}},{"code_sha256_prefix":"476ee9ec95271a06","entry":"probe_tokenizer_path_from_pretrained","repo":"siyuanhuang95/manipvqa","repo_kind":"official","path":"accessory/model/tokenizer.py","file_url":"https://github.com/siyuanhuang95/manipvqa/blob/HEAD/accessory/model/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"476ee9ec95271a06"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}