11 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; 10 failures of our instrument; 1 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/2405.05949.json · badge: /api/ran/2405.05949.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 |
|---|---|---|
| shi-labs/cumo | canonical (classifier label) classifier basis: census |
11 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| collate_fn | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/eval/model_vqa_loader.py code served (permissive licence) · get_code("20e4f665698a3d18") 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 tuple. 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.
|
| divide_to_patches | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/mm_utils.py code served (permissive licence) · get_code("7e03b180fa317c9a") 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 list, ndim 4, 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.
|
| get_chunk | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/eval/model_vqa.py code served (permissive licence) · get_code("42a46570620cd9fa") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, 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.
|
| get_most_similar | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/eval/calculate_score.py code served (permissive licence) · get_code("c28eb86a8d14e4ed") 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 str. 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.
|
| is_none | Ran ran, violated the contract we drafted |
shi-labs/cumo/cumo/eval/model_vqa_mmbench.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from ASTRAL-Group/ASTRA, is pointer only (licence: NONE) · get_code("bae18947b56f2be1") 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 ASTRAL-Group/ASTRA, 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. |
| normalize_extracted_answer | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/eval/calculate_score.py code served (permissive licence) · get_code("ff5aa85ec44db5ee") 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 str. 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.
|
| process_single_sample | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/eval/model_vqa_mathvista.py code served (permissive licence) · get_code("d6888be4b2989f1f") 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.
|
| read_json | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/eval/calculate_score.py code served (permissive licence) · get_code("9ffa907555068ff3") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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.
|
| resize_and_pad_image | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/mm_utils.py code served (permissive licence) · get_code("468eedeba67f1b00") 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 Image. 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.
|
| select_best_resolution | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shi-labs/cumo/cumo/mm_utils.py code served (permissive licence) · get_code("3999ff487573f32c") 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 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.
|
| split_list | Ran ran; our contract draft was wrong, not the code |
shi-labs/cumo/cumo/eval/model_vqa.py code served (permissive licence) · get_code("076c252c52cbb161") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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.
|
| construct_prompt | Not yet run unverified (harvested, no recorded run) |
shi-labs/cumo/cumo/eval/model_vqa_mathvista.py code served (permissive licence) · get_code("ed80aaedae521e4f") How it ranno 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, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 9 the same month, 10 later) and 2 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 |
|---|---|---|---|
| split_list | 197 other papers 51 dated earlier, 8 the same month, 131 later, 6 same year, order not determinable, 1 undated |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2306.17107 (2023-06) LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding 2307.10490 (2023-07) Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs and 194 more not named here |
| get_chunk | 189 other papers 49 dated earlier, 8 the same month, 126 later, 6 same year, order not determinable |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2306.17107 (2023-06) LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding 2307.10490 (2023-07) Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs and 186 more not named here |
| is_none | 83 other papers 23 dated earlier, 4 the same month, 54 later, 2 same year, order not determinable |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2308.10253 (2023-08) StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data 2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM and 80 more not named here |
| select_best_resolution | 73 other papers 9 dated earlier, 5 the same month, 59 later · 7 only as an assembly brick |
2106.06909 (2021-06) GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio |
2304.08485 (2023-04) Visual Instruction Tuning 2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM and 70 more not named here |
| resize_and_pad_image | 65 other papers 8 dated earlier, 4 the same month, 53 later |
2106.06909 (2021-06) GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio |
2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM 2310.08588 (2023-10) Octopus: Embodied Vision-Language Programmer from Environmental Feedback and 62 more not named here |
| divide_to_patches | 64 other papers 8 dated earlier, 4 the same month, 52 later |
2106.06909 (2021-06) GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio |
2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM 2310.08588 (2023-10) Octopus: Embodied Vision-Language Programmer from Environmental Feedback and 61 more not named here |
| collate_fn | 54 other papers 8 dated earlier, 2 the same month, 44 later |
2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM |
2310.08588 (2023-10) Octopus: Embodied Vision-Language Programmer from Environmental Feedback 2311.07362 (2023-11) Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision and 51 more not named here |
| get_most_similar | 7 other papers 1 dated earlier, 1 the same month, 5 later |
2403.03003 (2024-03) Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models |
2405.15574 (2024-05) Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models 2409.00147 (2024-09) MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models and 4 more not named here |
| read_json | 6 other papers 1 dated earlier, 5 later |
2402.16379 (2024-02) TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement |
2409.00147 (2024-09) MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models 2410.17885 (2024-10) Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning and 3 more not named here |
| normalize_extracted_answer | 3 other papers 1 dated earlier, 1 the same month, 1 later |
2403.03003 (2024-03) Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models |
2405.15574 (2024-05) Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models 2409.00147 (2024-09) MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models |
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 advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks. However, these scaling approaches are computationally expensive and overlook the significance of improving model capabilities from the vision side. Inspired by the successful applications of Mixture-of-Experts (MoE) in LLMs, which improves model scalability during training while keeping inference costs similar to those of smaller models, we propose CuMo. CuMo incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into both the vision encoder and the MLP connector, thereby enhancing the multimodal LLMs with minimal additional activated parameters during inference. CuMo first pre-trains the MLP blocks and then initializes each expert in the MoE block from the pre-trained MLP block during the visual instruction tuning stage. Auxiliary losses are used to ensure a balanced loading of experts. CuMo outperforms state-of-the-art multimodal LLMs across various VQA and visual-instruction-following benchmarks using models within each model size group, all while training exclusively on open-sourced datasets. The code and model weights for CuMo are open-sourced at https://github.com/SHI-Labs/CuMo.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.05949")
get_code_for_paper("2405.05949")
have("2405.05949")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2405.05949.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2405.05949)
Connect an agent — have() is free.