{"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/position-enhanced-visual-instruction-tuning","title":"Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models","arxiv_id":"2308.13437","date":"2023-08-25","proceeding":null,"authors":["Chi Chen","Ruoyu Qin","Fuwen Luo","Xiaoyue Mi","Peng Li","Maosong Sun","Yang Liu"],"abstract":"Recently, Multimodal Large Language Models (MLLMs) that enable Large Language Models (LLMs) to interpret images through visual instruction tuning have achieved significant success. However, existing visual instruction tuning methods only utilize image-language instruction data to align the language and image modalities, lacking a more fine-grained cross-modal alignment. In this paper, we propose Position-enhanced Visual Instruction Tuning (PVIT), which extends the functionality of MLLMs by integrating an additional region-level vision encoder. This integration promotes a more detailed comprehension of images for the MLLM. In addition, to efficiently achieve a fine-grained alignment between the vision modules and the LLM, we design multiple data generation strategies to construct an image-region-language instruction dataset. Finally, we present both quantitative experiments and qualitative analysis that demonstrate the superiority of the proposed model. Code and data will be released at https://github.com/PVIT-official/PVIT.","url_abs":"https://arxiv.org/abs/2308.13437v2","url_pdf":"https://arxiv.org/pdf/2308.13437v2.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":"position-enhanced-visual-instruction-tuning","repo_url":"https://github.com/pvit-official/pvit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Position"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.13437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13437"}},"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/pvit-official/pvit","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":3},"by_repo_kind":{"official":{"samples":11,"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":11,"samples":[{"code_sha256_prefix":"a50ecc5d0cfbcfdc","entry":"convert_from_prompt_tokens","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/model/prompt_model.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/model/prompt_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":"a50ecc5d0cfbcfdc"}},{"code_sha256_prefix":"ece52dd9fc04a887","entry":"convert_from_prompt_tokens","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/run_cli.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/run_cli.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":"ece52dd9fc04a887"}},{"code_sha256_prefix":"5824bd7cca0f1a41","entry":"convert_from_prompt_tokens","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/run_fine_eval.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/run_fine_eval.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":"5824bd7cca0f1a41"}},{"code_sha256_prefix":"8631b6088b2cdc4d","entry":"convert_region_tags","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/conversation.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/conversation.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":"8631b6088b2cdc4d"}},{"code_sha256_prefix":"8669b33db98abe59","entry":"convert_to_plain_text_from_prompt_tokens","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/run_cli.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/run_cli.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":"8669b33db98abe59"}},{"code_sha256_prefix":"4f3fad7d68deccc3","entry":"convert_to_plain_text_from_prompt_tokens","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/run_fine_eval.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/run_fine_eval.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":"4f3fad7d68deccc3"}},{"code_sha256_prefix":"6c436b35bf74b36e","entry":"encode_img","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/run_cli.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/run_cli.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":"6c436b35bf74b36e"}},{"code_sha256_prefix":"ec1c3a7e61c6a678","entry":"encode_img","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/run_fine_eval.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/run_fine_eval.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":"ec1c3a7e61c6a678"}},{"code_sha256_prefix":"f3dac39e14527d0e","entry":"extract_region_feats","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/model/region_clip.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/model/region_clip.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":"f3dac39e14527d0e"}},{"code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/utils.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/utils.py","link_basis":"harvester_set","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":"37899f22fb191b37"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"pvit-official/pvit","repo_kind":"official","path":"pvit/utils.py","file_url":"https://github.com/pvit-official/pvit/blob/HEAD/pvit/utils.py","link_basis":"harvester_set","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":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}