SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.05271 · 2024

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Wenqi Shao, Xizhou Zhu, Lewei Lu, Jifeng Dai, Yu Qiao, Dahua Lin, Wenhai Wang, Kai Chen, Yue Cao, Hao Tian, Tong Lu, Bo Wang, and 30 more

arXiv · PDF · Open in the Atlas

Code that ran

1 of 9 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, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 8 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/2412.05271.json · badge: /api/ran/2412.05271.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
opengvlab/internvl marked official in Papers with Code
Papers with Code archive
1 ran · 8 no recorded run
FunctionStatusWhere it lives
InternRMSNorm Ran
ran on a synthesized input
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("93caa5f159d8d21e")
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 3, dtype family float, shape (2, 3, 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
from torch import nn

class InternRMSNorm(nn.Module):

    def __init__(self, hidden_size, eps=1e-06):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(hidden_size))
        self.variance_epsilon = eps

    def forward(self, hidden_states):
        input_dtype = hidden_states.dtype
        hidden_states = hidden_states.to(torch.float32)
        variance = hidden_states.pow(2).mean(-1, keepdim=True)
        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
        return self.weight * hidden_states.to(input_dtype)


INIT_ARGS = {
    'hidden_size': 4,
    'eps': 1e-06
}

ARGS = {
    'hidden_states': torch.randn(2, 3, 4)
}

if __name__ == '__main__':
    model = InternRMSNorm(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Input shape: {ARGS['hidden_states'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Output dtype: {output.dtype}")
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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)
FlashAttention Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("4820719786c9fe69")
How it ran

no invocation recorded.

InternAttention Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("96dc7d3f715cd025")
How it ran

no invocation recorded.

InternMLP Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("9e42410e4aedc241")
How it ran

no invocation recorded.

InternVisionConfig Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("61270c46a55bf470")
How it ran

no invocation recorded.

InternVisionEmbeddings Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("5e9c10fd95d0fa3d")
How it ran

no invocation recorded.

InternVisionEncoder Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("ebdef2adcb4093b4")
How it ran

no invocation recorded.

InternVisionEncoderLayer Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("57d717eaa96834d2")
How it ran

no invocation recorded.

InternVisionModel Not yet run
unverified (harvested, no recorded run)
opengvlab/internvl/internvl_chat/internvl/model/internvl_chat/modeling_intern_vit.py
code served (permissive licence) · get_code("f2ebe5ff9e470826")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 5 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
InternAttention
brick of this paper's assembly: model
1 other paper
1 later
2503.02304 (2025-03)
A Token-level Text Image Foundation Model for Document Understanding
InternMLP
brick of this paper's assembly: model
1 other paper
1 later
2503.02304 (2025-03)
A Token-level Text Image Foundation Model for Document Understanding
InternRMSNorm
brick of this paper's assembly: model
1 other paper
1 later
2503.02304 (2025-03)
A Token-level Text Image Foundation Model for Document Understanding
InternVisionConfig
brick of this paper's assembly: helper
1 other paper
1 later
2503.02304 (2025-03)
A Token-level Text Image Foundation Model for Document Understanding

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 introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. In this work, we delve into the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and testtime configurations. Through extensive evaluations on a wide range of benchmarks, including multi-discipline reasoning, document understanding, multi-image / video understanding, realworld comprehension, multimodal hallucination detection, visual grounding, multilingual capabilities, and pure language processing, InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. Notably, our model is the first open-source MLLMs to surpass 70% on the MMMU benchmark, achieving a 3.7-point improvement through Chain-of-Thought (CoT) reasoning and showcasing strong potential for test-time scaling. HuggingFace demo see https://huggingface.co/ spaces/OpenGVLab/InternVL

For agents

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

get_harvested_code_for_paper("2412.05271")
get_code_for_paper("2412.05271")
have("2412.05271")

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

curl https://syntology.ai/api/ran/2412.05271.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.05271.svg)](https://syntology.ai/paper/2412.05271)

Connect an agent — have() is free.