SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.12191 · 2024

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Peng Wang, Dayiheng Liu, Chang Zhou, Junyang Lin, Jingren Zhou, Xuancheng Ren, Shijie Wang, Jinze Bai, Shuai Bai, Kai Dang, Yang Fan, Wenbin Ge, and 7 more

arXiv · PDF · Open in the Atlas

Code that ran

12 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 4 failures of our instrument; 0 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/2409.12191.json · badge: /api/ran/2409.12191.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
yangyucheng000/University community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
QwenLM/Qwen2-VL community
Papers with Code archive
4 ran · 0 no recorded run
MindCode-4/code-4 community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
baichuan-inc/Baichuan-Omni-1.5 community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
whitespace_tokenize Ran
ran; our contract draft was wrong, not the code
MindCode-4/code-4/prophetnet/tokenization_prophetnet.py
code served (permissive licence) · get_code("cf9ffa02a42184af")
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 list, ndim 1, dtype family float; no output shape is stated. 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 2026-09-05T02:55:57Z). 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
import numpy as np

def whitespace_tokenize(text):
    """Runs basic whitespace cleaning and splitting on a piece of text."""
    text = text.strip()
    if not text:
        return []
    tokens = text.split()
    return tokens

# Setup code
torch.manual_seed(0)

# The function takes a single parameter: text (a string)
# It performs basic whitespace cleaning and splitting
# We need to provide a valid string argument

ARGS = {
    "text": "  hello world  this is a test  "
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — 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 float — 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
RotaryEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
baichuan-inc/Baichuan-Omni-1.5/baichuan-omni/model/modeling_omni.py
code served (permissive licence) · get_code("7bc2a2784aabedc7")
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, RotaryEmbedding: 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)

# RotaryEmbedding expects:
# - dim: int (embedding dimension, must be even for the implementation)
# - max_position_embeddings: int (default 2048)
# - base: float (default 5000000.0)
# - device: device or None

ARGS = {
    "dim": 8,
    "max_position_embeddings": 128,
    "base": 10000.0,
    "device": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
deepspeed, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RotaryEmbedding — 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 RotaryEmbedding 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
ceil_by_factor Ran
ran, honoured the contract we drafted
QwenLM/Qwen2-VL/qwen-vl-utils/src/qwen_vl_utils/vision_process.py
code served (permissive licence) · get_code("6e45201fa27cb24a")
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 int, ndim 0, dtype family int, shape () 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 math

def ceil_by_factor(number: int, factor: int) -> int:
    """Returns the smallest integer greater than or equal to 'number' that is divisible by 'factor'."""
    return math.ceil(number / factor) * factor

ARGS = {
    "number": 10,
    "factor": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 int, ndim 0, dtype family int, shape () — shape () 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
floor_by_factor Ran
ran, honoured the contract we drafted
QwenLM/Qwen2-VL/qwen-vl-utils/src/qwen_vl_utils/vision_process.py
code served (permissive licence) · get_code("8155263d7ff19bb3")
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 int, ndim 0, dtype family int, shape () 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 math

ARGS = {
    "number": 17,
    "factor": 5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 int, ndim 0, dtype family int, shape () — shape () 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
flow_color Ran
ran on a synthesized input
yangyucheng000/University/JDRL-mindspore/flowfunction.py
code served (permissive licence) · get_code("6ccf5863fa0f0c9d")
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 ndarray, ndim 4, dtype family float, shape (2, 1, 4, 3) 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 numpy as np
import torch

# Create a mock flow tensor
# flow_color expects input shape [batch, channels, height, width]
# where channels=2 (u, v components)
batch_size = 2
height = 4
width = 3
channels = 2

# Create a simple flow array with u and v components
flow = np.random.randn(batch_size, channels, height, width).astype(np.float32)

# Create a mock object that has asnumpy() method (like MXNet NDArray)
class MockFlowTensor:
    def __init__(self, data):
        self.data = data
    
    def asnumpy(self):
        return self.data
    
    @property
    def shape(self):
        return self.data.shape
    
    def __getitem__(self, idx):
        return MockFlowTensor(self.data[idx])

# Wrap the flow in mock tensor
mock_flow = MockFlowTensor(flow)

ARGS = {
    "flow": mock_flow
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 4, 3) 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
flow_compute_color Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yangyucheng000/University/JDRL-mindspore/flowfunction.py
code served (permissive licence) · get_code("63c5a2b51dee1425")
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) 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 numpy as np

# Create small test flow fields (u and v components)
# Shape: (4, 3) for height=4, width=3
u = np.random.randn(4, 3).astype(np.float32) * 5
v = np.random.randn(4, 3).astype(np.float32) * 5

# Test with convert_to_bgr=False (default RGB)
ARGS = {
    "u": u,
    "v": v,
    "convert_to_bgr": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 3) 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
flow_to_color Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yangyucheng000/University/JDRL-mindspore/flowfunction.py
code served (permissive licence) · get_code("c869c75bbde6fc92")
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) 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 numpy as np

# Create a small optical flow field with shape [H, W, 2]
# H=4, W=3 for distinct dimensions
H, W = 4, 3
flow_uv = np.random.randn(H, W, 2).astype(np.float32) * 10

ARGS = {
    "flow_uv": flow_uv,
    "clip_flow": 5.0,
    "convert_to_bgr": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 3) 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
is_image_file Ran
ran, violated the contract we drafted
yangyucheng000/University/JDRL-mindspore/dataset_RGB.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from invokerer/deeprft, is pointer only (licence: NOASSERTION) · get_code("91fca7a2b44569ad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from invokerer/deeprft, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

load_vocab Ran
ran; our contract draft was wrong, not the code
MindCode-4/code-4/prophetnet/tokenization_prophetnet.py
code served (permissive licence) · get_code("e7fbc7a74a3457c7")
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 OrderedDict. 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 collections
import tempfile
import os

# Create a temporary vocabulary file
temp_dir = tempfile.mkdtemp()
vocab_file = os.path.join(temp_dir, 'vocab.txt')

# Write some sample tokens to the vocab file
sample_tokens = ['[PAD]', '[UNK]', '[CLS]', '[SEP]', 'the', 'quick', 'brown', 'fox']
with open(vocab_file, 'w', encoding='utf-8') as f:
    for token in sample_tokens:
        f.write(token + '\n')

ARGS = {
    'vocab_file': vocab_file
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
round_by_factor Ran
ran, honoured the contract we drafted
QwenLM/Qwen2-VL/qwen-vl-utils/src/qwen_vl_utils/vision_process.py
code served (permissive licence) · get_code("e252767324188623")
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 int, ndim 0, dtype family int, shape () 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 numpy as np

# Analyze the function:
# round_by_factor(number: int, factor: int) -> int
# The function takes two integers and returns an integer.
# It divides number by factor, rounds to nearest integer, then multiplies by factor.

# Set up arguments
number_arg = 17
factor_arg = 5

ARGS = {
    "number": number_arg,
    "factor": factor_arg,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () 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
smart_resize Ran
ran, honoured the contract we drafted
QwenLM/Qwen2-VL/qwen-vl-utils/src/qwen_vl_utils/vision_process.py
code served (permissive licence) · get_code("464fd25cf4b2eac6")
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 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
from typing import Optional, Tuple

# Set up arguments for smart_resize function
ARGS = {
    "height": 480,
    "width": 640,
    "factor": 16,
    "min_pixels": None,
    "max_pixels": None,
}
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 tuple, ndim 1, dtype family int — 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
train Ran
ran on a synthesized input
yangyucheng000/University/PDF_MS/trainner.py
code served (permissive licence) · get_code("2fe12723d2eed03d")
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 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Stand-in batch class with required attributes
class Batch:
    def __init__(self, bg, feats, bases, labels):
        self.bg = bg
        self.feats = feats
        self.bases = bases
        self.labels = labels

# Stand-in graph object with get_batched_graph method
class Graph:
    def get_batched_graph(self):
        # Return tuple of graph-related tensors (unpacked with *)
        return (torch.randn(2, 4), torch.randn(2, 3))

# Stand-in train_net callable that accepts feats, bases, labels, and graph outputs
class TrainNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 1)
    
    def forward(self, feats, bases, labels, *graph_outputs):
        # Consume all arguments and return a scalar loss
        loss = self.linear(feats).sum() + bases.sum() + labels.sum()
        for tensor in graph_outputs:
            loss = loss + tensor.sum()
        return loss

# Build the dataloader
feats = torch.randn(2, 4)
bases = torch.randn(2, 3)
labels = torch.randn(2, 1)
bg = Graph()

batch = Batch(bg=bg, feats=feats, bases=bases, labels=labels)
dataloader = [batch]

# Build the model (can be any nn.Module, used only for type consistency)
model = nn.Linear(4, 1)

# Build train_net
train_net = TrainNet()

ARGS = {
    "model": model,
    "dataloader": dataloader,
    "train_net": train_net
}
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 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

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, 8 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 later) and 4 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
whitespace_tokenize 43 other papers
37 dated earlier, 5 later, 1 same year, order not determinable
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
and 40 more not named here
load_vocab 29 other papers
25 dated earlier, 4 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
and 26 more not named here
round_by_factor
brick of this paper's assembly: helper
25 other papers
24 later, 1 undated
2410.11623 (2024-10)
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
2412.01720 (2024-12)
LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant
2025.acl-long.1603 (2025 (year only))
Design Choices for Extending the Context Length of Visual Language Models
and 22 more not named here
ceil_by_factor
brick of this paper's assembly: helper
23 other papers
22 later, 1 undated
2410.11623 (2024-10)
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
2412.01720 (2024-12)
LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant
2025.acl-long.1603 (2025 (year only))
Design Choices for Extending the Context Length of Visual Language Models
and 20 more not named here
floor_by_factor
brick of this paper's assembly: helper
23 other papers
22 later, 1 undated
2410.11623 (2024-10)
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
2412.01720 (2024-12)
LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant
2025.acl-long.1603 (2025 (year only))
Design Choices for Extending the Context Length of Visual Language Models
and 20 more not named here
flow_to_color 5 other papers
5 dated earlier
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
2010.14851 (2020-10)
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
2104.00556 (2021-04)
Deep Two-View Structure-from-Motion Revisited
and 2 more not named here
is_image_file 5 other papers
4 dated earlier, 1 same year, order not determinable
Zhang_Learning_Rain_Location_Prior_for_Nighttime_Deraining_ICCV_2023_paper (2023 (year only))
Learning Rain Location Prior for Nighttime Deraining
2308.03867 (2023-08)
From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal
2309.03063 (2023-09)
Prompt-based Ingredient-Oriented All-in-One Image Restoration
and 2 more not named here
flow_compute_color 2 other papers
2 dated earlier
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1612.01925 (2016-12)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

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

We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. This approach allows the model to generate more efficient and accurate visual representations, closely aligning with human perceptual processes. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos. We employ a unified paradigm for processing both images and videos, enhancing the model's visual perception capabilities. To explore the potential of large multimodal models, Qwen2-VL investigates the scaling laws for large vision-language models (LVLMs). By scaling both the model size-with versions at 2B, 8B, and 72B parameters-and the amount of training data, the Qwen2-VL Series achieves highly competitive performance. Notably, the Qwen2-VL-72B model achieves results comparable to leading models such as GPT-4o and Claude3.5-Sonnet across various multimodal benchmarks, outperforming other generalist models. Code is available at https://github.com/QwenLM/Qwen2-VL.

For agents

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

get_harvested_code_for_paper("2409.12191")
get_code_for_paper("2409.12191")
have("2409.12191")

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

curl https://syntology.ai/api/ran/2409.12191.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.12191.svg)](https://syntology.ai/paper/2409.12191)

Connect an agent — have() is free.