Papers › STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering

STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering

28 Jun 2024arXiv:2406.19973archive 2025-07-28

Guohao Sun, Can Qin, Huazhu Fu, Linwei Wang, Zhiqiang Tao

Large Vision-Language Models (LVLMs) have shown significant potential in assisting medical diagnosis by leveraging extensive biomedical datasets. However, the advancement of medical image understanding and reasoning critically depends on building high-quality visual instruction data, which is costly and labor-intensive to obtain, particularly in the medical domain. To mitigate this data-starving issue, we introduce Self-Training Large Language and Vision Assistant for Medicine (STLLaVA-Med). The proposed method is designed to train a policy model (an LVLM) capable of auto-generating medical visual instruction data to improve data efficiency, guided through Direct Preference Optimization (DPO). Specifically, a more powerful and larger LVLM (e.g., GPT-4o) is involved as a biomedical expert to oversee the DPO fine-tuning process on the auto-generated data, encouraging the policy model to align efficiently with human preferences. We validate the efficacy and data efficiency of STLLaVA-Med across three major medical Visual Question Answering (VQA) benchmarks, demonstrating competitive zero-shot performance with the utilization of only 9% of the medical data.

PaperPDFCodeCode Syntology ranMethod as code

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 19 code samples harvested from 1 repository linked to this paper: 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 9 ran (5 with no instrument failure; 4 where Syntology's instrument failed). 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 9 samples that ran have no recorded date.

heliossun/stllava-med officialmentioned in papermentioned on GitHubpytorchMITSyntology: 19 samples, 9 ran (4 instrument-failed) · 10 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

19 samples harvested: 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
1ran; the contract check could not run
5ran
10unverified

Licence: 0 of the 19 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 heliossun/stllava-med. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

heliossun/stllava-med official repository 19 samples, 9 ran (4 instrument-failed) · 10 unverified
CLIPVisionTower in 11 papers llava/model/language_model/llava_llama.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · ee3792b1ae45cbb6 · report fixture: returned CLIPVisionTower · level recorded 2026-09-22
Clustering llava/model/language_model/llava_llama.py ran · metamorphic tier: deterministic MIT (permissive) · b2d62e11a466c119 · report fixture: returned Clustering · level recorded 2026-09-22
IdentityMap llava/model/language_model/llava_llama.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 9f0f5d62445adabe · report fixture: returned IdentityMap · level recorded 2026-09-22
LlavaConfig in 6 papers llava/model/language_model/llava_llama.py ran · metamorphic tier: deterministic MIT (permissive) · e9cfb7ae423d3e3a · report fixture: returned LlavaConfig · level recorded 2026-09-22
QuickGELU in 5 papers llava/model/language_model/llava_llama.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 990ae00bb84c8cce · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
build_vision_projector in 23 papers llava/model/language_model/llava_llama.py ran · our draft was wrong MIT (permissive) · fba2ee2fd7519dce · report fixture: signature config:MockConfig/0/?, delay_load:bool/0/bool · returned Clustering · level recorded 2026-09-22
get_chunk in 197 papers llava/eval/model_cap.py ran · our draft was wrong fingerprinted MIT (permissive) · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
split_list in 223 papers llava/eval/model_cap.py ran · our draft was wrong fingerprinted MIT (permissive) · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
split_to_even_chunks in 41 papers llava_dpo_trainer.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 10893c4608c08075 · report fixture: signature indices:list/1/int, lengths:dict/0/?, num_chunks:int/0/int · returned list · level recorded, date not recorded
LlavaLlamaForCausalLM in 15 papers llava/model/language_model/llava_llama.py unverified MIT (permissive) · 846e78137649eefe · report
LlavaLlamaModel in 13 papers llava/model/language_model/llava_llama.py unverified MIT (permissive) · 7687df6fa2a321f7 · report
LlavaMetaForCausalLM in 16 papers llava/model/language_model/llava_llama.py unverified MIT (permissive) · 9392f432fde94da9 · report
LlavaMetaModel in 16 papers llava/model/language_model/llava_llama.py unverified MIT (permissive) · 616ce829130b1d59 · report
build_vision_tower in 35 papers llava/model/language_model/llava_llama.py unverified MIT (permissive) · b95671438fbf50fa · report
get_mm_adapter_state_maybe_zero_3 in 44 papers llava_dpo_trainer.py unverified MIT (permissive) · bb35e3ac741bb2c9 · report
get_peft_state_maybe_zero_3 in 31 papers train_dpo.py unverified MIT (permissive) · fa1225dfac92bc0d · report
get_peft_state_non_lora_maybe_zero_3 in 24 papers train_dpo.py unverified MIT (permissive) · 1c53657305b66e9f · report
maybe_zero_3 in 74 papers llava_dpo_trainer.py unverified MIT (permissive) · 735025744c1ab0cf · report
maybe_zero_3 in 74 papers train_dpo.py unverified MIT (permissive) · 616ffbdc154ed2d8 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for STLLaVA-Med (graph method: STLLaVA-Med). 11 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. LlavaLlamaForCausalLM entry · level 0 · unverified · 846e78137649eefe
  2. LlavaConfig helper · level 1 · ran · e9cfb7ae423d3e3a
  3. LlavaLlamaModel model · level 0 · unverified · 7687df6fa2a321f7
  4. LlavaMetaForCausalLM helper · level 0 · unverified · 9392f432fde94da9
  5. LlavaMetaModel helper · level 0 · unverified · 616ce829130b1d59
  6. build_vision_projector helper · level 1 · ran · our draft was wrong · fba2ee2fd7519dce
  7. build_vision_tower helper · level 0 · unverified · b95671438fbf50fa
  8. Clustering helper · level 1 · ran · b2d62e11a466c119
  9. IdentityMap helper · level 1 · ran · 9f0f5d62445adabe
  10. CLIPVisionTower helper · level 1 · ran · ee3792b1ae45cbb6
  11. QuickGELU helper · level 1 · ran · 990ae00bb84c8cce

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.19973") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Medical DiagnosisMedical Visual Question AnsweringQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

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

ALIGNDPO

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