{"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/honeybee-locality-enhanced-projector-for","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","arxiv_id":"2312.06742","date":"2023-12-11","proceeding":"CVPR 2024 1","authors":["Junbum Cha","Wooyoung Kang","Jonghwan Mun","Byungseok Roh"],"abstract":"In Multimodal Large Language Models (MLLMs), a visual projector plays a crucial role in bridging pre-trained vision encoders with LLMs, enabling profound visual understanding while harnessing the LLMs' robust capabilities. Despite the importance of the visual projector, it has been relatively less explored. In this study, we first identify two essential projector properties: (i) flexibility in managing the number of visual tokens, crucial for MLLMs' overall efficiency, and (ii) preservation of local context from visual features, vital for spatial understanding. Based on these findings, we propose a novel projector design that is both flexible and locality-enhanced, effectively satisfying the two desirable properties. Additionally, we present comprehensive strategies to effectively utilize multiple and multifaceted instruction datasets. Through extensive experiments, we examine the impact of individual design choices. Finally, our proposed MLLM, Honeybee, remarkably outperforms previous state-of-the-art methods across various benchmarks, including MME, MMBench, SEED-Bench, and LLaVA-Bench, achieving significantly higher efficiency. Code and models are available at https://github.com/kakaobrain/honeybee.","url_abs":"https://arxiv.org/abs/2312.06742v2","url_pdf":"https://arxiv.org/pdf/2312.06742v2.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":"honeybee-locality-enhanced-projector-for","repo_url":"https://github.com/kakaobrain/honeybee","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"mme","task_name":"MME"},{"task_slug":"science-question-answering","task_name":"Science Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/science-question-answering-on-scienceqa","task":"Science Question Answering","dataset":"ScienceQA","model":"Honeybee","rank_in_archive_order":2,"of":10,"metrics":{"Avg. Accuracy":"94.39","Grades 1-6":"95.04","Grades 7-12":"93.21","Image Context":"93.75","Language Science":"91.18","Natural Science":"95.20","No Context":"93.17","Social Science":"96.29","Text Context":"94.48"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.06742","atlas_url":"https://app.syntology.ai/?focus=2312.06742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06742"}},"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/kakaobrain/honeybee","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"8e96a129037194be","entry":"get_media_indices","repo":"kakaobrain/honeybee","repo_kind":"official","path":"honeybee/modeling_honeybee.py","file_url":"https://github.com/kakaobrain/honeybee/blob/HEAD/honeybee/modeling_honeybee.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8e96a129037194be"}},{"code_sha256_prefix":"15e54d5d53ab90ac","entry":"post_process_code","repo":"kakaobrain/honeybee","repo_kind":"official","path":"serve/model_utils.py","file_url":"https://github.com/kakaobrain/honeybee/blob/HEAD/serve/model_utils.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":"15e54d5d53ab90ac"}},{"code_sha256_prefix":"607a861da4671ce5","entry":"post_process_output","repo":"kakaobrain/honeybee","repo_kind":"official","path":"serve/model_utils.py","file_url":"https://github.com/kakaobrain/honeybee/blob/HEAD/serve/model_utils.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":"607a861da4671ce5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}