{"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/from-seeing-to-doing-bridging-reasoning-and","title":"From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation","arxiv_id":"2505.08548","date":"2025-05-13","proceeding":null,"authors":["Yifu Yuan","Haiqin Cui","Yibin Chen","Zibin Dong","Fei Ni","Longxin Kou","Jinyi Liu","Pengyi Li","Yan Zheng","Jianye Hao"],"abstract":"Achieving generalization in robotic manipulation remains a critical challenge, particularly for unseen scenarios and novel tasks. Current Vision-Language-Action (VLA) models, while building on top of general Vision-Language Models (VLMs), still fall short of achieving robust zero-shot performance due to the scarcity and heterogeneity prevalent in embodied datasets. To address these limitations, we propose FSD (From Seeing to Doing), a novel vision-language model that generates intermediate representations through spatial relationship reasoning, providing fine-grained guidance for robotic manipulation. Our approach combines a hierarchical data pipeline for training with a self-consistency mechanism that aligns spatial coordinates with visual signals. Through extensive experiments, we comprehensively validated FSD's capabilities in both \"seeing\" and \"doing,\" achieving outstanding performance across 8 benchmarks for general spatial reasoning and embodied reference abilities, as well as on our proposed more challenging benchmark VABench. We also verified zero-shot capabilities in robot manipulation, demonstrating significant performance improvements over baseline methods in both SimplerEnv and real robot settings. Experimental results show that FSD achieves 40.6% success rate in SimplerEnv and 72% success rate across 8 real-world tasks, outperforming the strongest baseline by 30%.","url_abs":"https://arxiv.org/abs/2505.08548v2","url_pdf":"https://arxiv.org/pdf/2505.08548v2.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":"from-seeing-to-doing-bridging-reasoning-and","repo_url":"https://github.com/pickxiguapi/embodied-fsd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"},{"task_slug":"vision-language-action","task_name":"Vision-Language-Action"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.08548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.08548"}},"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/pickxiguapi/embodied-fsd","reach":null}],"summary":{"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":"0c3b510516f70000","entry":"convert_points_to_image_coords","repo":"pickxiguapi/embodied-fsd","repo_kind":"official","path":"affordance_point_inference_example.py","file_url":"https://github.com/pickxiguapi/embodied-fsd/blob/HEAD/affordance_point_inference_example.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c3b510516f70000"}},{"code_sha256_prefix":"8ffd85ac1c4837ac","entry":"parse_points_from_answer","repo":"pickxiguapi/embodied-fsd","repo_kind":"official","path":"affordance_point_inference_example.py","file_url":"https://github.com/pickxiguapi/embodied-fsd/blob/HEAD/affordance_point_inference_example.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":"8ffd85ac1c4837ac"}},{"code_sha256_prefix":"db73aee1947618bc","entry":"visualize_visual_trace","repo":"pickxiguapi/embodied-fsd","repo_kind":"official","path":"visual_trace_inference_example.py","file_url":"https://github.com/pickxiguapi/embodied-fsd/blob/HEAD/visual_trace_inference_example.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":"db73aee1947618bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}