SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.19973 · EMNLP · 2024

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

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

arXiv · PDF · Open in the Atlas

Code that ran

9 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 4 failures of our instrument; 10 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.19973.json · badge: /api/ran/2406.19973.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
heliossun/stllava-med canonical (classifier label)
classifier basis not recorded on the link
3 ran · 5 no recorded run
heliossun/STLLaVA-Med community
Papers with Code archive
6 ran · 5 no recorded run
FunctionStatusWhere it lives
CLIPVisionTower Ran
ran on a synthesized input · constructed an object; no result was computed
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("ee3792b1ae45cbb6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, CLIPVisionTower: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from transformers import CLIPVisionModel, CLIPImageProcessor, CLIPVisionConfig

torch.manual_seed(0)

# Create a minimal args object with required attributes
class Args:
    def __init__(self):
        self.mm_vision_select_layer = -2
        self.mm_vision_select_feature = 'patch'
        self.unfreeze_mm_vision_tower = False

# Create a minimal mock CLIPVisionConfig
class MockCLIPVisionConfig:
    def __init__(self):
        self.hidden_size = 768
        self.image_size = 224
        self.patch_size = 16
        self.num_hidden_layers = 12
    
    @classmethod
    def from_pretrained(cls, model_name):
        return cls()

# Create a minimal mock CLIPImageProcessor
class MockCLIPImageProcessor:
    def __call__(self, images, return_tensors=None):
        return images
    
    @classmethod
    def from_pretrained(cls, model_name):
        return cls()

# Create a minimal mock CLIPVisionModel
class MockCLIPVisionModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.config = MockCLIPVisionConfig()
        self._dtype = torch.float32
        self._device = torch.device('cpu')
        self.linear = nn.Linear(768, 768)
    
    def forward(self, pixel_values, output_hidden_states=False):
        batch_size = pixel_values.shape[0]
        # Return object with hidden_states attribute
        class Output:
            def __init__(self, hidden_states):
                self.hidden_states = hidden_states
        
        # Create hidden states: list of tensors for different layers
        # Each layer has shape (batch_size, num_patches + 1, hidden_size)
        num_patches = 196  # (224/16)^2 = 196, plus 1 for cls token
        hidden_states = [
            torch.randn(batch_size, num_patches + 1, 768) for _ in range(12)
        ]
        return Output(hidden_states)
    
    def requires_grad_(self, requires_grad):
        for param in self.parameters():
            param.requires_grad = requires_grad
        return self
    
    @property
    def dtype(self):
        return self._dtype
    
    @property
    def device(self):
        return self._device

# Patch the transformers module classes for testing
def mock_from_pretrained(cls, model_name, device_map=None):
    return cls()

# Monkey patch the from_pretrained methods
original_clip_config_from_pretrained = CLIPVisionConfig.from_pretrained
original_clip_processor_from_pretrained = CLIPImageProcessor.from_pretrained
original_clip_model_from_pretrained = CLIPVisionModel.from_pretrained

CLIPVisionConfig.from_pretrained = classmethod(lambda cls, model_name: MockCLIPVisionConfig())
CLIPImageProcessor.from_pretrained = classmethod(lambda cls, model_name: MockCLIPImageProcessor())
CLIPVisionModel.from_pretrained = classmethod(lambda cls, model_name, device_map=None: MockCLIPVisionModel())

# Create arguments
ARGS = {
    'vision_tower': 'openai/clip-vit-base-patch16',
    'args': Args(),
    'delay_load': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CLIPVisionTower — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CLIPVisionTower output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Clustering Ran
ran on a synthesized input · constructed an object; no result was computed
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("b2d62e11a466c119")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, Clustering: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define the Clustering module parameters
channels = 4
channels_out = 8
num_centers = 3
num_clusters = 2

ARGS = {
    'channels': channels,
    'channels_out': channels_out,
    'num_centers': num_centers,
    'num_clusters': num_clusters,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Clustering — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Clustering output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
IdentityMap Ran
ran on a synthesized input · constructed an object; no result was computed
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("9f0f5d62445adabe")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, IdentityMap: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type IdentityMap — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a IdentityMap output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
LlavaConfig Ran
ran on a synthesized input · constructed an object; no result was computed
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("e9cfb7ae423d3e3a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, LlavaConfig: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from transformers import AutoConfig, LlamaConfig

torch.manual_seed(0)

ARGS = {
    "architectures": ["LlavaForCausalLM"],
    "attention_bias": False,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 128,
    "initializer_range": 0.02,
    "intermediate_size": 256,
    "max_position_embeddings": 512,
    "model_type": "llava",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 2,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "rope_scaling": None,
    "rope_theta": 10000.0,
    "rms_norm_eps": 1e-6,
    "tie_word_embeddings": False,
    "torch_dtype": "float32",
    "transformers_version": "4.30.0",
    "use_cache": True,
    "vocab_size": 256,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LlavaConfig — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a LlavaConfig output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
QuickGELU Ran
ran on a synthesized input
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("990ae00bb84c8cce")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

class QuickGELU(nn.Module):

    def forward(self, x: torch.Tensor):
        return x * torch.sigmoid(1.702 * x)


INIT_ARGS = {}

ARGS = {
    'x': torch.randn(2, 4)
}

if __name__ == '__main__':
    model = QuickGELU(**INIT_ARGS)
    output = model(**ARGS)
    print(output)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
build_vision_projector Ran
ran; our contract draft was wrong, not the code
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("fba2ee2fd7519dce")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Clustering. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class MockConfig:
    def __init__(self):
        self.mm_hidden_size = 4
        self.hidden_size = 3
        self.mm_projector_type = 'cluster'

# Create a config object with the required attributes
config = MockConfig()

# Define ARGS dict with all parameters for build_vision_projector
ARGS = {
    'config': config,
    'delay_load': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Clustering — a Clustering output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Clustering output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_chunk Ran
ran; our contract draft was wrong, not the code
heliossun/stllava-med/llava/eval/model_cap.py
code served (permissive licence) · get_code("42a46570620cd9fa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

def split_list(lst, n):
    """Split a list into n (roughly) equal-sized chunks"""
    chunk_size = math.ceil(len(lst) / n)
    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]

def get_chunk(lst, n, k):
    chunks = split_list(lst, n)
    return chunks[k]

# Setup code
lst = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
n = 3
k = 1

ARGS = {
    "lst": lst,
    "n": n,
    "k": k
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
split_list Ran
ran; our contract draft was wrong, not the code
heliossun/stllava-med/llava/eval/model_cap.py
code served (permissive licence) · get_code("076c252c52cbb161")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

def split_list(lst, n):
    """Split a list into n (roughly) equal-sized chunks"""
    chunk_size = math.ceil(len(lst) / n)
    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]

# Setup code
lst = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
n = 3

ARGS = {
    "lst": lst,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
split_to_even_chunks Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
heliossun/stllava-med/llava_dpo_trainer.py
code served (permissive licence) · get_code("10893c4608c08075")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyzing the function:
# - indices: a list/sequence of indices that will be iterated over
# - lengths: a dict-like or list-like object that maps indices to their lengths (accessed via lengths[index])
# - num_chunks: an integer specifying how many chunks to split into

# Create sample data
indices = [0, 1, 2, 3, 4, 5]
lengths = {0: 10, 1: 15, 2: 8, 3: 12, 4: 9, 5: 11}
num_chunks = 3

ARGS = {
    "indices": indices,
    "lengths": lengths,
    "num_chunks": num_chunks,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
LlavaLlamaForCausalLM Not yet run
unverified (harvested, no recorded run)
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("846e78137649eefe")
How it ran

no invocation recorded.

LlavaLlamaModel Not yet run
unverified (harvested, no recorded run)
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("7687df6fa2a321f7")
How it ran

no invocation recorded.

LlavaMetaForCausalLM Not yet run
unverified (harvested, no recorded run)
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("9392f432fde94da9")
How it ran

no invocation recorded.

LlavaMetaModel Not yet run
unverified (harvested, no recorded run)
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("616ce829130b1d59")
How it ran

no invocation recorded.

build_vision_tower Not yet run
unverified (harvested, no recorded run)
heliossun/STLLaVA-Med/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("b95671438fbf50fa")
How it ran

no invocation recorded.

get_mm_adapter_state_maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
heliossun/stllava-med/llava_dpo_trainer.py
code served (permissive licence) · get_code("bb35e3ac741bb2c9")
How it ran

no invocation recorded.

get_peft_state_maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
heliossun/stllava-med/train_dpo.py
code served (permissive licence) · get_code("fa1225dfac92bc0d")
How it ran

no invocation recorded.

get_peft_state_non_lora_maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
heliossun/stllava-med/train_dpo.py
code served (permissive licence) · get_code("1c53657305b66e9f")
How it ran

no invocation recorded.

maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
heliossun/stllava-med/llava_dpo_trainer.py
code served (permissive licence) · get_code("735025744c1ab0cf")
How it ran

no invocation recorded.

maybe_zero_3 Not yet run
unverified (harvested, no recorded run)
heliossun/stllava-med/train_dpo.py
code served (permissive licence) · get_code("616ffbdc154ed2d8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 12 the same month, 13 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
split_list 197 other papers
60 dated earlier, 22 the same month, 108 later, 6 same year, order not determinable, 1 undated
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2306.17107 (2023-06)
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
2307.10490 (2023-07)
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
and 194 more not named here
get_chunk 189 other papers
58 dated earlier, 21 the same month, 104 later, 6 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2306.17107 (2023-06)
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
2307.10490 (2023-07)
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
and 186 more not named here
QuickGELU
brick of this paper's assembly: helper
62 other papers
40 dated earlier, 22 later · 59 only as an assembly brick
1902.00751 (2019-02)
Parameter-Efficient Transfer Learning for NLP
2011.10566 (2020-11)
Exploring Simple Siamese Representation Learning
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
and 59 more not named here
get_mm_adapter_state_maybe_zero_3 43 other papers
15 dated earlier, 4 the same month, 24 later
2304.05884 (2023-04)
Unicom: Universal and Compact Representation Learning for Image Retrieval
2304.08485 (2023-04)
Visual Instruction Tuning
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
and 40 more not named here
maybe_zero_3 42 other papers
16 dated earlier, 4 the same month, 22 later
2304.05884 (2023-04)
Unicom: Universal and Compact Representation Learning for Image Retrieval
2304.08485 (2023-04)
Visual Instruction Tuning
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
and 39 more not named here
split_to_even_chunks 40 other papers
14 dated earlier, 4 the same month, 22 later
2304.05884 (2023-04)
Unicom: Universal and Compact Representation Learning for Image Retrieval
2304.08485 (2023-04)
Visual Instruction Tuning
2310.03744 (2023-10)
Improved Baselines with Visual Instruction Tuning
and 37 more not named here
maybe_zero_3 37 other papers
13 dated earlier, 4 the same month, 20 later
2310.01779 (2023-10)
HallE-Control: Controlling Object Hallucination in Large Multimodal Models
2311.16839 (2023-11)
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
2312.02949 (2023-12)
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models
and 34 more not named here
get_peft_state_maybe_zero_3 23 other papers
7 dated earlier, 2 the same month, 14 later
2310.01779 (2023-10)
HallE-Control: Controlling Object Hallucination in Large Multimodal Models
2401.02330 (2024-01)
LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model
2402.12501 (2024-02)
Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection
and 20 more not named here
get_peft_state_non_lora_maybe_zero_3 23 other papers
7 dated earlier, 3 the same month, 13 later
2310.01779 (2023-10)
HallE-Control: Controlling Object Hallucination in Large Multimodal Models
2312.02949 (2023-12)
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models
2401.02330 (2024-01)
LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model
and 20 more not named here
IdentityMap
brick of this paper's assembly: helper
19 other papers
6 dated earlier, 4 the same month, 9 later · 18 only as an assembly brick
2301.12597 (2023-01)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
2304.08485 (2023-04)
Visual Instruction Tuning
2306.02858 (2023-06)
Video-LLaMA An Instruction-tuned Audio-Visual Language Model for Video Understanding
and 16 more not named here
LlavaLlamaModel
brick of this paper's assembly: model
13 other papers
3 dated earlier, 2 the same month, 8 later · 3 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2404.05673 (2024-04)
CoReS: Orchestrating the Dance of Reasoning and Segmentation
2405.14974 (2024-05)
LOVA 3 : Learning to Visual Question Answering, Asking and Assessment
and 10 more not named here
LlavaConfig
brick of this paper's assembly: helper
12 other papers
6 dated earlier, 1 the same month, 5 later · 9 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2309.17102 (2023-09)
Guiding Instruction-based Image Editing via Multimodal Large Language Models
2402.18695 (2024-02)
Grounding Language Models for Visual Entity Recognition
and 9 more not named here
CLIPVisionTower
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 1 the same month, 1 later · 3 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2406.20095 (2024-06)
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
2502.13508 (2025-02)
VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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. Our implementation is available at https: //github.com/heliossun/STLLaVA-Med.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.19973")
get_code_for_paper("2406.19973")
have("2406.19973")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.19973.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.19973.svg)](https://syntology.ai/paper/2406.19973)

Connect an agent — have() is free.