Papers › Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

8 May 2025arXiv:2505.05464archive 2025-07-28

Shiqi Chen, Jinghan Zhang, Tongyao Zhu, Wei Liu, Siyang Gao, Miao Xiong, Manling Li, Junxian He

Vision-Language Models (VLMs) combine visual perception with the general capabilities, such as reasoning, of Large Language Models (LLMs). However, the mechanisms by which these two abilities can be combined and contribute remain poorly understood. In this work, we explore to compose perception and reasoning through model merging that connects parameters of different models. Unlike previous works that often focus on merging models of the same kind, we propose merging models across modalities, enabling the incorporation of the reasoning capabilities of LLMs into VLMs. Through extensive experiments, we demonstrate that model merging offers a successful pathway to transfer reasoning abilities from LLMs to VLMs in a training-free manner. Moreover, we utilize the merged models to understand the internal mechanism of perception and reasoning and how merging affects it. We find that perception capabilities are predominantly encoded in the early layers of the model, whereas reasoning is largely facilitated by the middle-to-late layers. After merging, we observe that all layers begin to contribute to reasoning, whereas the distribution of perception abilities across layers remains largely unchanged. These observations shed light on the potential of model merging as a tool for multimodal integration and interpretation.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2505.05464")

Code

Syntology Ran 10 of 11 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · our draft was wrong; 4 ran · fixture could not drive it.

By repository: official repository: 11 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shiqichen17/vlm_merging officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 10 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
4ran · fixture could not drive it
1unverified

Licence: 11 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from shiqichen17/vlm_merging. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate_majority_sign_mask shiqichen17/vlm_merging/merge.py official repository ran · our draft was wrong no licence file found · pointer only · b46f6a6e9e499e42 · report
dare_linear shiqichen17/vlm_merging/merge.py official repository ran · fixture could not drive it no licence file found · pointer only · a2577df9ddbdf691 · report
dare_ties shiqichen17/vlm_merging/merge.py official repository ran · fixture could not drive it no licence file found · pointer only · 90236229f79c5ceb · report
disjoint_merge shiqichen17/vlm_merging/merge.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 9eeb21ee73863b3b · report
extract_layer_number shiqichen17/vlm_merging/merge.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 01e735fa95b0a1a9 · report
magnitude_based_pruning shiqichen17/vlm_merging/merge.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · a527bf2700a78e15 · report
prune shiqichen17/vlm_merging/merge.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 6caa545d200ee863 · report
random_pruning shiqichen17/vlm_merging/merge.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 37b2d5955b59dbdd · report
reshape_weight_task_tensors shiqichen17/vlm_merging/merge.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 96438568fea309ce · report
ties shiqichen17/vlm_merging/merge.py official repository ran · fixture could not drive it no licence file found · pointer only · 0683b00fee94ac33 · report
merge_models shiqichen17/vlm_merging/merge.py official repository unverified no licence file found · pointer only · f2ca9ea81cadf810 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections