SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.17422 · ICLR · 2025

MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs

Filip Ilievski, Mahyar Khayatkhoei, Jiarui Zhang, Prateek Chhikara

arXiv · PDF · Open in the Atlas

Code that ran

None of the 4 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (4 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/2502.17422.json · badge: /api/ran/2502.17422.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
saccharomycetes/mllms_know canonical (classifier label)
classifier basis: classifier_2025
0 ran · 4 no recorded run
FunctionStatusWhere it lives
gradient_attention_blip Not yet run
unverified (harvested, no recorded run)
saccharomycetes/mllms_know/blip_methods.py
pointer only (licence: NONE) · get_code("bb900c772c6f1d52")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saccharomycetes/mllms_know 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.

gradient_attention_llava Not yet run
unverified (harvested, no recorded run)
saccharomycetes/mllms_know/llava_methods.py
pointer only (licence: NONE) · get_code("7fc110d39ccd73b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saccharomycetes/mllms_know 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.

rel_attention_llava Not yet run
unverified (harvested, no recorded run)
saccharomycetes/mllms_know/llava_methods.py
pointer only (licence: NONE) · get_code("9339b87ca7b94e8a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saccharomycetes/mllms_know 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.

rel_attention_qwen2_5 Not yet run
unverified (harvested, no recorded run)
saccharomycetes/mllms_know/qwen2_5_methods.py
pointer only (licence: NONE) · get_code("2400d04c7898702b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saccharomycetes/mllms_know 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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) have experienced rapid progress in visual recognition tasks in recent years. Given their potential integration into many critical applications, it is important to understand the limitations of their visual perception. In this work, we study whether MLLMs can perceive small visual details as effectively as large ones when answering questions about images. We observe that their performance is very sensitive to the size of the visual subject of the question, and further show that this effect is in fact causal by conducting an intervention study. Next, we study the attention patterns of MLLMs when answering visual questions, and intriguingly find that they consistently know where to look, even when they provide the wrong answer. Based on these findings, we then propose training-free visual intervention methods that leverage the internal knowledge of any MLLM itself, in the form of attention and gradient maps, to enhance its perception of small visual details. We evaluate our proposed methods on two widely-used MLLMs and seven visual question answering benchmarks and show that they can significantly improve MLLMs' accuracy without requiring any training. Our results elucidate the risk of applying MLLMs to visual recognition tasks concerning small details and indicate that visual intervention using the model's internal state is a promising direction to mitigate this risk. 1

For agents

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

get_harvested_code_for_paper("2502.17422")
get_code_for_paper("2502.17422")
have("2502.17422")

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

curl https://syntology.ai/api/ran/2502.17422.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.17422.svg)](https://syntology.ai/paper/2502.17422)

Connect an agent — have() is free.