SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.04152 · ICLR · 2024

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions

Hanwang Zhang, Yueting Zhuang, Tat-Seng Chua, Wei Ji, Juncheng Li, Siliang Tang, Kaihang Pan, Zhiqi Ge, Minghe Gao, Wenqiao Zhang

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 9 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2308.04152.json · badge: /api/ran/2308.04152.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
DCDmllm/Cheetah canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DCDmllm/Cheetah/Cheetah/cheetah/models/modeling_llama2.py
code served (permissive licence) · get_code("30d7eec482ebf6b1")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 6, 5, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:09:20Z). 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

torch.manual_seed(0)

# Create a tensor with shape (batch, num_key_value_heads, seqlen, head_dim)
# Using distinct sizes: batch=2, num_key_value_heads=3, seqlen=5, head_dim=4
hidden_states = torch.randn(2, 3, 5, 4)

# n_rep is the repetition factor
n_rep = 2

ARGS = {
    "hidden_states": hidden_states,
    "n_rep": n_rep,
}
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 Tensor, ndim 4, dtype family float, shape (2, 6, 5, 4) — shape (2, 6, 5, 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: none by the harness; any seed is in the setup block
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DCDmllm/Cheetah/Cheetah/cheetah/models/modeling_llama2.py
code served (permissive licence) · get_code("f725bc2d76076485")
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 tuple, ndim 5, dtype family float; 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)

# Create small tensors for q and k
# Shape: (batch_size=2, seq_len=3, hidden_dim=4)
q = torch.randn(2, 3, 4)
k = torch.randn(2, 3, 4)

# Create cos and sin tensors
# The function squeezes dimensions 1 and 0, then indexes by position_ids
# So we need shape that allows this: (1, 1, seq_len, hidden_dim)
cos = torch.randn(1, 1, 5, 4)
sin = torch.randn(1, 1, 5, 4)

# Create position_ids
# Shape: (batch_size=2, seq_len=3)
position_ids = torch.tensor([[0, 1, 2], [1, 2, 3]])

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
    "position_ids": position_ids,
}
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 tuple, ndim 5, dtype family float — a tuple 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
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DCDmllm/Cheetah/Cheetah/cheetah/models/modeling_llama.py
code served (permissive licence) · get_code("9b4dff79d5e6102c")
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 tuple, ndim 5, dtype family float; 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)

# Analyze the function to understand tensor shapes:
# q, k: used in element-wise operations with cos, sin
# cos, sin: gathered using position_ids, shape [batch, heads, seq_len, dim]
# position_ids: shape [batch, seq_len], used to gather from cos/sin at dim 2

batch_size = 2
num_heads = 3
seq_len = 4
head_dim = 4

# q and k: [batch, heads, seq_len, head_dim]
q = torch.randn(batch_size, num_heads, seq_len, head_dim)
k = torch.randn(batch_size, num_heads, seq_len, head_dim)

# cos and sin: [1, heads, seq_len, head_dim] (will be repeated to batch_size)
cos = torch.randn(1, num_heads, seq_len, head_dim)
sin = torch.randn(1, num_heads, seq_len, head_dim)

# position_ids: [batch, seq_len] with values in range [0, seq_len)
position_ids = torch.tensor([
    [0, 1, 2, 3],
    [0, 1, 2, 3]
], dtype=torch.long)

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
    "position_ids": position_ids,
}
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 tuple, ndim 5, dtype family float — a tuple 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
collate_fn Ran
ran; our contract draft was wrong, not the code
DCDmllm/Cheetah/Cheetah/i4_cheetah_llama2.py
code served (permissive licence) · get_code("35a6b606c9a3cff3")
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 dict. 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)

# Create sample data structures that match what collate_fn expects
sample1 = {
    'sample_id': 'sample_001',
    'context': 'This is the first context',
    'raw_img_list': [torch.randn(3, 4, 4), torch.randn(3, 4, 4)],
    'response': 'First response'
}

sample2 = {
    'sample_id': 'sample_002',
    'context': 'This is the second context',
    'raw_img_list': [torch.randn(3, 4, 4)],
    'response': 'Second response'
}

sample3 = {
    'sample_id': 'sample_003',
    'context': 'This is the third context',
    'raw_img_list': [torch.randn(3, 4, 4), torch.randn(3, 4, 4), torch.randn(3, 4, 4)],
    'response': 'Third response'
}

# Create a batch as a list of samples
batch = [sample1, sample2, sample3]

ARGS = {
    'batch': batch
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
disabled_train Ran
ran, violated the contract we drafted
DCDmllm/Cheetah/Cheetah/cheetah/models/blip2.py
code served (permissive licence) · get_code("4cb732f513d69dfd")
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 SimpleModel. 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 SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

ARGS = {
    "self": model,
    "mode": True
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
main_process Ran
ran; our contract draft was wrong, not the code
DCDmllm/Cheetah/Cheetah/cheetah/common/dist_utils.py
code served (permissive licence) · get_code("98589643273920ba")
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 function. 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
import functools

torch.manual_seed(0)

def get_dist_info():
    import torch.distributed as dist
    if torch.__version__ < '1.0':
        initialized = dist._initialized
    else:
        initialized = dist.is_initialized()
    if initialized:
        rank = dist.get_rank()
        world_size = dist.get_world_size()
    else:
        rank = 0
        world_size = 1
    return (rank, world_size)

def main_process(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        rank, _ = get_dist_info()
        if rank == 0:
            return func(*args, **kwargs)
    return wrapper

# Create a simple test function to decorate
def sample_function(x, y):
    return x + y

# Apply the decorator
decorated_func = main_process(sample_function)

# The main_process function takes a single parameter: func (a callable)
ARGS = {
    'func': sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
node_to_dict Ran
ran; our contract draft was wrong, not the code
DCDmllm/Cheetah/Cheetah/cheetah/common/config.py
code served (permissive licence) · get_code("791c72070c0b1cfb")
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 dict. 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.

from omegaconf import OmegaConf

# Create a simple OmegaConf node to pass to node_to_dict
# The function converts an OmegaConf node to a regular Python container
node = OmegaConf.create({
    "model": {
        "name": "test_model",
        "layers": 3,
        "hidden_dim": 128
    },
    "training": {
        "lr": 0.001,
        "epochs": 100,
        "batch_size": 32
    },
    "data": ["sample1", "sample2", "sample3"]
})

ARGS = {
    "node": node
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
omegaconf — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
rotate_half Ran
ran; our contract draft was wrong, not the code
DCDmllm/Cheetah/Cheetah/cheetah/models/modeling_llama.py
code served (permissive licence) · get_code("b99eea6376d1e212")
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 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

torch.manual_seed(0)

# The function rotate_half takes a single parameter 'x' which is a tensor
# It accesses x.shape[-1] to get the last dimension
# It uses indexing with [..., :] slicing notation
# It calls torch.cat() to concatenate tensors

# Create a small tensor with shape (2, 4) - batch size 2, hidden dim 4
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 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: none by the harness; any seed is in the setup block
tile Ran
ran; our contract draft was wrong, not the code
DCDmllm/Cheetah/Cheetah/cheetah/models/base_model.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from MengzhouLu/RetroMPA, is pointer only (licence: NONE) · get_code("cb33571427334815")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from MengzhouLu/RetroMPA, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

zero_module Ran
ran; our contract draft was wrong, not the code
DCDmllm/Cheetah/Cheetah/cheetah/models/cheetah_llama2.py
code served (permissive licence) · get_code("4719c763c53be3fe")
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 SimpleModule. 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)

# Create a simple nn.Module with some parameters
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.conv = nn.Conv1d(2, 5, 3)
    
    def forward(self, x):
        return x

module = SimpleModule()

ARGS = {
    "module": module
}
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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
all_gather_with_grad Not yet run
unverified (harvested, no recorded run)
DCDmllm/Cheetah/Cheetah/cheetah/models/base_model.py
code served (permissive licence) · get_code("0ec9fc2025c16f65")
How it ran

no invocation recorded.

download_cached_file Not yet run
unverified (harvested, no recorded run)
DCDmllm/Cheetah/Cheetah/cheetah/common/dist_utils.py
code served (permissive licence) · get_code("643539116e049080")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 10 the same month, 11 later) and 1 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
rotate_half 360 other papers
16 dated earlier, 7 the same month, 334 later, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv 243 other papers
6 dated earlier, 1 the same month, 234 later, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
zero_module 196 other papers
61 dated earlier, 2 the same month, 132 later, 1 same year, order not determinable · 49 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
and 193 more not named here
disabled_train 173 other papers
36 dated earlier, 7 the same month, 130 later · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
all_gather_with_grad 91 other papers
12 dated earlier, 5 the same month, 74 later · 2 only as an assembly brick
2206.02967 (2022-06)
Masked Unsupervised Self-training for Label-free Image Classification
2210.08773 (2022-10)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
2302.06605 (2023-02)
UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
and 88 more not named here
tile 84 other papers
15 dated earlier, 4 the same month, 65 later
2206.07699 (2022-06)
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
2210.07795 (2022-10)
EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
2210.08773 (2022-10)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
and 81 more not named here
apply_rotary_pos_emb 83 other papers
5 dated earlier, 78 later · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here
apply_rotary_pos_emb 47 other papers
6 dated earlier, 5 the same month, 36 later
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
2305.16355 (2023-05)
PandaGPT: One Model To Instruction-Follow Them All
and 44 more not named here
node_to_dict 39 other papers
5 dated earlier, 2 the same month, 32 later
2305.04160 (2023-05)
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
and 36 more not named here
download_cached_file 37 other papers
5 dated earlier, 2 the same month, 30 later
2305.04160 (2023-05)
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
and 34 more not named here
main_process 35 other papers
5 dated earlier, 2 the same month, 28 later
2305.04160 (2023-05)
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
and 32 more not named here

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

Recent advancements in Multimodal Large Language Models (MLLMs) have been utilizing Visual Prompt Generators (VPGs) to convert visual features into tokens that LLMs can recognize. This is achieved by training the VPGs on millions of image-caption pairs, where the VPG-generated tokens of images are fed into a frozen LLM to generate the corresponding captions. However, this image-captioning based training objective inherently biases the VPG to concentrate solely on the primary visual contents sufficient for caption generation, often neglecting other visual details. This shortcoming results in MLLMs' underperformance in comprehending demonstrative instructions consisting of multiple, interleaved, and multimodal instructions that demonstrate the required context to complete a task. To address this issue, we introduce a generic and lightweight Visual Prompt Generator Complete module (VPG-C), which can infer and complete the missing details essential for comprehending demonstrative instructions. Further, we propose a synthetic discriminative training strategy to fine-tune VPG-C, eliminating the need for supervised demonstrative instructions. As for evaluation, we build DEMON, a comprehensive benchmark for demonstrative instruction understanding. Synthetically trained with the proposed strategy, VPG-C achieves significantly stronger zero-shot performance across all tasks of DEMON. Further evaluation on the MME and OwlEval benchmarks also demonstrate the superiority of VPG-C. The code and models are available at https://github.com/DCDmllm/Cheetah.

For agents

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

get_harvested_code_for_paper("2308.04152")
get_code_for_paper("2308.04152")
have("2308.04152")

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

curl https://syntology.ai/api/ran/2308.04152.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.04152.svg)](https://syntology.ai/paper/2308.04152)

Connect an agent — have() is free.