Papers › Honeybee: Locality-enhanced Projector for Multimodal LLM

Honeybee: Locality-enhanced Projector for Multimodal LLM

11 Dec 2023CVPR 2024 1arXiv:2312.06742archive 2025-07-28

Junbum Cha, Wooyoung Kang, Jonghwan Mun, Byungseok Roh

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2312.06742")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kakaobrain/honeybee officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran

Licence: 3 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from kakaobrain/honeybee. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_media_indices kakaobrain/honeybee/honeybee/modeling_honeybee.py official repository ran licence not identified · pointer only · 8e96a129037194be · report
post_process_code kakaobrain/honeybee/serve/model_utils.py official repository ran fingerprinted no licence file found · pointer only · 15e54d5d53ab90ac · report
post_process_output kakaobrain/honeybee/serve/model_utils.py official repository ran fingerprinted no licence file found · pointer only · 607a861da4671ce5 · report

Tasks

MMEScience Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Science Question Answering ScienceQA Honeybee Avg. Accuracy 94.39 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee Grades 1-6 95.04 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee Grades 7-12 93.21 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee Image Context 93.75 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee Language Science 91.18 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee Natural Science 95.20 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee No Context 93.17 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee Social Science 96.29 #2 of 10 Archive leaderboard report
Science Question Answering ScienceQA Honeybee Text Context 94.48 #2 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections