Zhao Wang, Wei-Yao Wang, Helen Suzuki, Yoshiyuki Kobayashi, Ai2 Molmo
6 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; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 6 no recorded run), measured 2026-11-22; 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/2503.02597.json · badge: /api/ran/2503.02597.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.
| Repository | Role | Ran |
|---|---|---|
| sony/aki | canonical (classifier label) classifier basis: classifier_2025 |
6 ran · 6 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| DecoupledEmbedding | Ran ran on a synthesized input |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("fba7faec475b6155") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. |
| DecoupledLinear | Ran ran on a synthesized input |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("496711093e515803") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. |
| PerceiverResampler | Ran ran on a synthesized input |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("0159490d2bc73030") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. |
| getattr_recursive | Ran ran; our contract draft was wrong, not the code |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("fe68fff801021b23") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. |
| num_params | Ran ran, honoured the contract we drafted |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("660aaca8fc241af6") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. |
| stack_with_padding | Ran ran, honoured the contract we drafted |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("5960fdbe295db3b4") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. |
| AKI | Not yet run unverified (harvested, no recorded run) |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("a2c6bf85eabc2a2d") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. No invocation recorded. |
| VLM | Not yet run unverified (harvested, no recorded run) |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("54e0b46f8fc75e1f") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. No invocation recorded. |
| VLMOutputWithPast | Not yet run unverified (harvested, no recorded run) |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("d3d41f8bfc075e11") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. No invocation recorded. |
| VLMWithLanguageStream | Not yet run unverified (harvested, no recorded run) |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("05e29a0f3f27ca4d") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. No invocation recorded. |
| VisionTokenizer | Not yet run unverified (harvested, no recorded run) |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("710431cb836ef89c") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. No invocation recorded. |
| stack_with_padding_2D_attention | Not yet run unverified (harvested, no recorded run) |
sony/aki/codes/open_flamingo/src/modeling_aki.py pointer only (licence: NOASSERTION) · get_code("ca93e9c39ec815ad") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sony/aki (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. No invocation recorded. |
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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| getattr_recursive brick of this paper's assembly: helper |
5 other papers 5 dated earlier · 1 only as an assembly brick |
2308.02463 (2023-08) Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data |
2310.00647 (2023-10) Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning 2402.10805 (2024-02) Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond and 2 more not named here |
| VLMOutputWithPast brick of this paper's assembly: helper |
1 other paper 1 dated earlier |
2402.10805 (2024-02) Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond |
|
| VisionTokenizer brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2402.10805 (2024-02) Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond |
|
| num_params brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2402.10805 (2024-02) Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in MLLMs has emerged as a critical challenge, where the textual responses generated by these models are not factually aligned with the given text-image inputs. Existing efforts to address vision-language misalignment have focused on developing specialized vision-language connectors or leveraging visual instruction tuning from diverse domains. In this paper, we tackle this issue from a fundamental yet unexplored perspective by revisiting the core architecture of MLLMs. Most MLLMs are typically built on decoder-only LLMs consisting of a causal attention mechanism, which limits the ability of the earlier modalities (e.g., images) to incorporate information from the latter modalities (e.g., text). To address this problem a MLLM that unlocks causal attention into our proposed modality-mutual attention (MMA) to enable image tokens to attend to text tokens. This simple yet effective design allows MMA to achieve state-of-the-art performance in 12 multimodal understanding benchmarks (+6.2% on average across 3 LLMs backbones) without introducing additional parameters. Our MMA design is intended to be generic, allowing for applications across various modalities, and scalable to accommodate diverse multimodal scenarios. The codebase is available at https://github.com/sony/aki.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2503.02597")
get_code_for_paper("2503.02597")
have("2503.02597")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2503.02597.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2503.02597)
Connect an agent — have() is free.