3 of 7 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 2 have no contract verdict; 0 failures of our instrument; 4 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/2501.06986.json · badge: /api/ran/2501.06986.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 |
|---|---|---|
| mozhgan91/leo | canonical (classifier label) classifier basis: plan_row |
3 ran · 4 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| version_cmp | Ran ran, violated the contract we drafted |
mozhgan91/leo/leo_chat/leo/model/leo_chat/modeling_internvl_chat.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from sotayang/svbench, is pointer only (licence: NONE) · get_code("5f3bdd5f3304a0e0") How it ranThe 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 sotayang/svbench, 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. |
| concat_pad_data_collator | Ran ran on a synthesized input |
mozhgan91/leo/leo_chat/leo/patch/pad_data_collator.py code served (permissive licence) · get_code("8b94520cd540e6d3") How it ranRan 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.
|
| pad_data_collator | Ran ran on a synthesized input |
mozhgan91/leo/leo_chat/leo/patch/pad_data_collator.py code served (permissive licence) · get_code("c98153c6978bb741") How it ranRan 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.
|
| apply_rotary_pos_emb | Not yet run unverified (harvested, no recorded run) |
mozhgan91/leo/leo_chat/leo/patch/llama2_flash_attn_monkey_patch.py code served (permissive licence) · get_code("3408dd47e939d760") How it ranno invocation recorded. |
| forward | Not yet run unverified (harvested, no recorded run) |
mozhgan91/leo/leo_chat/leo/patch/llama_flash_attn_monkey_patch.py code served (permissive licence) · get_code("021dddfe7e4fc462") How it ranno invocation recorded. |
| forward_2 | Not yet run unverified (harvested, no recorded run) |
mozhgan91/leo/leo_chat/leo/patch/llama_flash_attn_monkey_patch.py code served (permissive licence) · get_code("f67aecf10b83d6b9") How it ranno invocation recorded. |
| get_conv_template | Not yet run unverified (harvested, no recorded run) |
mozhgan91/leo/leo_chat/leo/conversation.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from yzy-bupt/LiveStar, is pointer only (licence: NONE) · get_code("04b172bb0c32a0de") How it ranThe 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 yzy-bupt/LiveStar, 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. No invocation recorded. |
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 6 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| get_conv_template | 69 other papers 51 dated earlier, 14 later, 3 same year, order not determinable, 1 undated |
1911.03705 (2019-11) CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory 2204.07705 (2022-04) SUPER-NATURALINSTRUCTIONS: Generalization via Declarative Instructions on 1600+ NLP Tasks and 66 more not named here |
| apply_rotary_pos_emb | 6 other papers 3 dated earlier, 2 later, 1 same year, order not determinable |
2309.17452 (2023-09) ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving |
2312.00401 (2023-12) VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things 2312.14187 (2023-12) WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning and 3 more not named here |
| version_cmp | 6 other papers 3 dated earlier, 3 later |
2410.16261 (2024-10) Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance |
2412.03324 (2024-12) A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs 2412.09616 (2024-12) V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding and 3 more not named here |
| forward | 1 other paper 1 later |
2503.14021 (2025-03) MP-GUI: Modality Perception with MLLMs for GUI Understanding |
|
| forward_2 | 1 other paper 1 later |
2503.14021 (2025-03) MP-GUI: Modality Perception with MLLMs for GUI Understanding |
|
| pad_data_collator | 1 other paper 1 later |
2503.14021 (2025-03) MP-GUI: Modality Perception with MLLMs for GUI 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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Mixture of Vision Encoders (MoVE) has emerged as a powerful approach to enhance the fine-grained visual understanding of multimodal large language models (MLLMs), improving their ability to handle tasks such as complex optical character recognition and scene understanding. Despite these advances, effectively combining diverse encoders and their visual tokens, while also scaling to high-resolution inputs, remains an open challenge. In this work, we conduct a systematic study of fusion designs for MoVE-based MLLMs, highlighting principles for token-level integration across complementary encoders. Our study shows that a lightweight recipe consisting of post-adaptation fusion with independent projectors, tile-level sequence interleaving, and dynamic tiling with global context delivers strong performance on diverse benchmarks. We integrate these principles into a simple and effective architecture that we call LEO. Extensive evaluation on 11 vision-language benchmarks demonstrates that LEO achieves better results on the majority of tasks compared to existing MoVE-based approaches. Furthermore, LEO adapts effectively to the specialized domain of autonomous driving without altering its architecture or training recipe, achieving competitive performance against established baselines and thereby highlighting its ability to generalize. The code is available at https://github.com/Mozhgan91/LEO.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.06986")
get_code_for_paper("2501.06986")
have("2501.06986")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2501.06986.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2501.06986)
Connect an agent — have() is free.