{"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/what-s-left-concept-grounding-with-logic","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","arxiv_id":"2310.16035","date":"2023-10-24","proceeding":null,"authors":["Joy Hsu","Jiayuan Mao","Joshua B. Tenenbaum","Jiajun Wu"],"abstract":"Recent works such as VisProg and ViperGPT have smartly composed foundation models for visual reasoning-using large language models (LLMs) to produce programs that can be executed by pre-trained vision-language models. However, they operate in limited domains, such as 2D images, not fully exploiting the generalization of language: abstract concepts like \"left\" can also be grounded in 3D, temporal, and action data, as in moving to your left. This limited generalization stems from these inference-only methods' inability to learn or adapt pre-trained models to a new domain. We propose the Logic-Enhanced Foundation Model (LEFT), a unified framework that learns to ground and reason with concepts across domains with a differentiable, domain-independent, first-order logic-based program executor. LEFT has an LLM interpreter that outputs a program represented in a general, logic-based reasoning language, which is shared across all domains and tasks. LEFT's executor then executes the program with trainable domain-specific grounding modules. We show that LEFT flexibly learns concepts in four domains: 2D images, 3D scenes, human motions, and robotic manipulation. It exhibits strong reasoning ability in a wide variety of tasks, including those that are complex and not seen during training, and can be easily applied to new domains.","url_abs":"https://arxiv.org/abs/2310.16035v1","url_pdf":"https://arxiv.org/pdf/2310.16035v1.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":"what-s-left-concept-grounding-with-logic","repo_url":"https://github.com/joyhsu0504/left","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"visual-question-answering-vqa-split-a","task_name":"Visual Question Answering (VQA) Split A"},{"task_slug":"visual-question-answering-vqa-split-b","task_name":"Visual Question Answering (VQA) Split B"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.16035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16035"}},"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/joyhsu0504/left","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"02f326c9c80bd20a","entry":"edge2mat","repo":"joyhsu0504/left","repo_kind":"official","path":"left/nn/agcn/agcn_graph.py","file_url":"https://github.com/joyhsu0504/left/blob/HEAD/left/nn/agcn/agcn_graph.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":"02f326c9c80bd20a"}},{"code_sha256_prefix":"78522d4b0690de25","entry":"get_spatial_graph","repo":"joyhsu0504/left","repo_kind":"official","path":"left/nn/agcn/agcn_graph.py","file_url":"https://github.com/joyhsu0504/left/blob/HEAD/left/nn/agcn/agcn_graph.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":"78522d4b0690de25"}},{"code_sha256_prefix":"abe9afd483b702d8","entry":"normalize_digraph","repo":"joyhsu0504/left","repo_kind":"official","path":"left/nn/agcn/agcn_graph.py","file_url":"https://github.com/joyhsu0504/left/blob/HEAD/left/nn/agcn/agcn_graph.py","link_basis":"harvester_set","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":"abe9afd483b702d8"}},{"code_sha256_prefix":"639c74e151322e56","entry":"optional_repeat","repo":"joyhsu0504/left","repo_kind":"official","path":"left/nn/point_net_pp/point_net_pp.py","file_url":"https://github.com/joyhsu0504/left/blob/HEAD/left/nn/point_net_pp/point_net_pp.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":"639c74e151322e56"}},{"code_sha256_prefix":"775337099d9f9b3c","entry":"break_up_pc","repo":"joyhsu0504/left","repo_kind":"official","path":"left/nn/point_net_pp/point_net_pp.py","file_url":"https://github.com/joyhsu0504/left/blob/HEAD/left/nn/point_net_pp/point_net_pp.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"775337099d9f9b3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}