SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.08640 · 2024

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 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/2408.08640.json · badge: /api/ran/2408.08640.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
wwzhuang01/math-puma canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
window_unpartition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wwzhuang01/math-puma/models/deepseek_math/sam.py
pointer only (licence: GPL-3.0) · get_code("7bca1adaded75dc9")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, wwzhuang01/math-puma, is not in the permissive set Syntology serves inline. 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.

create_siglip_vit Ran
ran on a synthesized input
wwzhuang01/math-puma/models/deepseek_math/siglip_vit.py
pointer only (licence: GPL-3.0) · get_code("a63c3596d1105d5d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, wwzhuang01/math-puma, is not in the permissive set Syntology serves inline. 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.

expand2square Ran
ran; our contract draft was wrong, not the code
wwzhuang01/math-puma/models/deepseek_math/image_processing_vlm.py
pointer only (licence: GPL-3.0) · get_code("592b3c1a88f93d7c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, wwzhuang01/math-puma, is not in the permissive set Syntology serves inline. 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.

get_rel_pos Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wwzhuang01/math-puma/models/deepseek_math/sam.py
pointer only (licence: GPL-3.0) · get_code("733d7f0bedcb74c2")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, wwzhuang01/math-puma, is not in the permissive set Syntology serves inline. 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.

window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wwzhuang01/math-puma/models/deepseek_math/sam.py
pointer only (licence: GPL-3.0) · get_code("5693c99bfc32e135")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, wwzhuang01/math-puma, is not in the permissive set Syntology serves inline. 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 2 the same month, 4 later) and 0 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
expand2square 68 other papers
39 dated earlier, 1 the same month, 25 later, 3 same year, order not determinable · 1 only as an assembly brick
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2204.03541 (2022-04)
End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation
2308.10253 (2023-08)
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
and 65 more not named here
get_rel_pos 47 other papers
36 dated earlier, 9 later, 2 same year, order not determinable · 5 only as an assembly brick
2304.02643 (2023-04)
Segment Anything
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
and 44 more not named here
window_partition 47 other papers
36 dated earlier, 1 the same month, 8 later, 2 same year, order not determinable · 1 only as an assembly brick
2304.02643 (2023-04)
Segment Anything
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
and 44 more not named here
window_unpartition 46 other papers
36 dated earlier, 8 later, 2 same year, order not determinable · 1 only as an assembly brick
2304.02643 (2023-04)
Segment Anything
2304.06790 (2023-04)
Inpaint Anything: Segment Anything Meets Image Inpainting
2304.12306 (2023-04)
Segment Anything in Medical Images
and 43 more not named here
create_siglip_vit 1 other paper
1 dated earlier
2403.05525 (2024-03)
DeepSeek-VL: Towards Real-World Vision-Language 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

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance problem-solving, but MLLMs perform worse as information shifts from textual to visual modality. This decline is mainly due to their shortcomings in aligning images and text. To tackle aforementioned challenges, we propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment. This approach is designed to improve the mathematical reasoning skills of MLLMs through a three-stage training process, with the second stage being the critical alignment stage. We first enhance the language model's mathematical reasoning capabilities with extensive set of textual mathematical problems. We then construct a multimodal dataset with varying degrees of textual and visual information, creating data pairs by presenting each problem in at least two forms. By leveraging the Kullback-Leibler (KL) divergence of next-token prediction distributions to align visual and textual modalities, consistent problem-solving abilities are ensured. Finally, we utilize multimodal instruction tuning for MLLMs with high-quality multimodal data. Experimental results on multiple mathematical reasoning benchmarks demonstrate that the MLLMs trained with Math-PUMA surpass most open-source MLLMs. Our approach effectively narrows the performance gap for problems presented in different modalities. The code and data are available at: \url{https://github.com/wwzhuang01/Math-PUMA}.

For agents

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

get_harvested_code_for_paper("2408.08640")
get_code_for_paper("2408.08640")
have("2408.08640")

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

curl https://syntology.ai/api/ran/2408.08640.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.08640.svg)](https://syntology.ai/paper/2408.08640)

Connect an agent — have() is free.