Papers › Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models

16 Apr 2024arXiv:2404.10237archive 2025-07-28

Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu

Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks, and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing, hindering their clinical utility across diverse resource-constrained scenarios in practice. In this paper, we propose a novel and lightweight framework Med-MoE (Mixture-of-Experts) that tackles both discriminative and generative multimodal medical tasks. The learning of Med-MoE consists of three steps: multimodal medical alignment, instruction tuning and routing, and domain-specific MoE tuning. After aligning multimodal medical images with LLM tokens, we then enable the model for different multimodal medical tasks with instruction tuning, together with a trainable router tailored for expert selection across input modalities. Finally, the model is tuned by integrating the router with multiple domain-specific experts, which are selectively activated and further empowered by meta expert. Comprehensive experiments on both open- and close-end medical question answering (Med-VQA) and image classification tasks across datasets such as VQA-RAD, SLAKE and Path-VQA demonstrate that our model can achieve performance superior to or on par with state-of-the-art baselines, while only requiring approximately 30%-50% of activated model parameters. Extensive analysis and ablations corroborate the effectiveness and practical utility of our method.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples: 10 from 2 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 12: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 2 repositories, 7 ran (2 with no instrument failure; 5 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 7 samples that ran have no recorded date.

jiangsongtao/med-moe officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
jiangsongtao/tinymed officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 6 ran (4 instrument-failed) · 3 unverified 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

12 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
5ran · our draft was wrong
1ran
5unverified

Licence: 2 of the 12 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

jiangsongtao/med-moe official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
MoEStablelmDecoderLayer_forward moellava/model/language_model/llava_stablelm_moe.py ran · our draft was wrong Apache-2.0 (permissive) · 0d5ea0366375f84c · report fixture: signature self:callable/0/? · returned function · level recorded 2026-09-22
jiangsongtao/tinymed official repository 9 samples, 6 ran (4 instrument-failed) · 3 unverified
einsum in 6 papers moe/sharded_moe.py ran Apache-2.0 (permissive) · 97286a837fefce75 · report fixture: signature rule:str/0/str, a:Tensor/1/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_chunk in 197 papers model_vqa_med.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
is_moe_param moe/utils.py ran · violated contract fingerprinted Apache-2.0 (permissive) · dee86097e6631190 · report fixture: signature param:Tensor/2/float · returned bool · level recorded 2026-09-24
load_jsonl in 179 papers run_eval.py ran · our draft was wrong Apache-2.0 (permissive) · 77678f2758141df9 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
split_list in 223 papers model_vqa_med.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
split_params_into_shared_and_expert_params moe/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 593d61d6861a857f · report fixture: signature params:list/1/Tensor · returned tuple · level recorded 2026-09-24
gumbel_rsample moe/sharded_moe.py unverified Apache-2.0 (permissive) · 3b6fa807ed00b1da · report
has_moe_layers moe/utils.py unverified Apache-2.0 (permissive) · d327fe6cbd808182 · report
multiplicative_jitter moe/sharded_moe.py unverified Apache-2.0 (permissive) · 765e66c4d56297b6 · report
Repository not located 2 samples, 0 ran · 2 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
save_image_to_local in 8 papers repository not located unverified licence of this copy not recorded · e2e5c3a95a6aebb4 · report
save_video_to_local in 8 papers repository not located unverified licence of this copy not recorded · 22930d58d32e2d08 · report

Tasks

Image ClassificationMixture-of-ExpertsQuestion AnsweringVisual Question Answering (VQA)image-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MoE

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