{"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/vocot-unleashing-visually-grounded-multi-step","title":"VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models","arxiv_id":"2405.16919","date":"2024-05-27","proceeding":null,"authors":["Zejun Li","Ruipu Luo","Jiwen Zhang","Minghui Qiu","Zhongyu Wei"],"abstract":"While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper proposes VoCoT, a multi-step Visually grounded object-centric Chain-of-Thought reasoning framework tailored for inference with LMMs. VoCoT is characterized by two key features: (1) object-centric reasoning paths that revolve around cross-modal shared object-level information, and (2) visually grounded representation of object concepts in a multi-modal interleaved and aligned manner, which effectively bridges the modality gap within LMMs during long-term generation. Additionally, we construct an instruction dataset to facilitate LMMs in adapting to reasoning with VoCoT. By introducing VoCoT into the prevalent open-source LMM architecture, we introduce VolCano. With only 7B parameters and limited input resolution, VolCano demonstrates excellent performance across various scenarios, surpassing SOTA models, including GPT-4V, in tasks requiring complex reasoning. Our code, data and model will be available at https://github.com/RupertLuo/VoCoT.","url_abs":"https://arxiv.org/abs/2405.16919v2","url_pdf":"https://arxiv.org/pdf/2405.16919v2.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":"vocot-unleashing-visually-grounded-multi-step","repo_url":"https://github.com/rupertluo/vocot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.16919","atlas_url":"https://app.syntology.ai/?focus=2405.16919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16919"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/rupertluo/vocot","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"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":10,"samples":[{"code_sha256_prefix":"18d6d9e2b67790b8","entry":"build_front_projector","repo":"rupertluo/vocot","repo_kind":"official","path":"model/front_projector/builder.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/model/front_projector/builder.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":"18d6d9e2b67790b8"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"rupertluo/vocot","repo_kind":"official","path":"model/language_model/volcano_base.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/model/language_model/volcano_base.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"e88a45d058f2a1cf","entry":"get_all_output_names","repo":"rupertluo/vocot","repo_kind":"official","path":"model/load_model.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/model/load_model.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":"e88a45d058f2a1cf"}},{"code_sha256_prefix":"4e236f3faab636da","entry":"get_output_name","repo":"rupertluo/vocot","repo_kind":"official","path":"model/load_model.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/model/load_model.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":"4e236f3faab636da"}},{"code_sha256_prefix":"6d3603f5bc8c308a","entry":"resize_image_to_square","repo":"rupertluo/vocot","repo_kind":"official","path":"model/language_model/volcano_mistral.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/model/language_model/volcano_mistral.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":"6d3603f5bc8c308a"}},{"code_sha256_prefix":"a5af183dc2d57ca3","entry":"split_tensor_func","repo":"rupertluo/vocot","repo_kind":"official","path":"model/language_model/volcano_base.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/model/language_model/volcano_base.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":"a5af183dc2d57ca3"}},{"code_sha256_prefix":"70d4d368dd8d9447","entry":"get_peft_state_maybe_zero_3","repo":"rupertluo/vocot","repo_kind":"official","path":"train_volcano.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/train_volcano.py","link_basis":"first_harvest_node","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":"70d4d368dd8d9447"}},{"code_sha256_prefix":"95fa5f303fe6207c","entry":"get_peft_state_non_lora_maybe_zero_3","repo":"rupertluo/vocot","repo_kind":"official","path":"train_volcano.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/train_volcano.py","link_basis":"first_harvest_node","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":"95fa5f303fe6207c"}},{"code_sha256_prefix":"ddaaa05f9112fe7c","entry":"init_Qformer","repo":"rupertluo/vocot","repo_kind":"official","path":"model/front_projector/builder.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/model/front_projector/builder.py","link_basis":"first_harvest_node","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":"ddaaa05f9112fe7c"}},{"code_sha256_prefix":"d10512f432705d71","entry":"maybe_zero_3","repo":"rupertluo/vocot","repo_kind":"official","path":"train_volcano.py","file_url":"https://github.com/rupertluo/vocot/blob/HEAD/train_volcano.py","link_basis":"first_harvest_node","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":"d10512f432705d71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}