Papers › Attention Prompting on Image for Large Vision-Language Models

Attention Prompting on Image for Large Vision-Language Models

25 Sep 2024arXiv:2409.17143archive 2025-07-28

Runpeng Yu, Weihao Yu, Xinchao Wang

Compared with Large Language Models (LLMs), Large Vision-Language Models (LVLMs) can also accept images as input, thus showcasing more interesting emergent capabilities and demonstrating impressive performance on various vision-language tasks. Motivated by text prompting in LLMs, visual prompting has been explored to enhance LVLMs' capabilities of perceiving visual information. However, previous visual prompting techniques solely process visual inputs without considering text queries, limiting the models' ability to follow text instructions to complete tasks. To fill this gap, in this work, we propose a new prompting technique named Attention Prompting on Image, which just simply overlays a text-query-guided attention heatmap on the original input image and effectively enhances LVLM on various tasks. Specifically, we generate an attention heatmap for the input image dependent on the text query with an auxiliary model like CLIP. Then the heatmap simply multiplies the pixel values of the original image to obtain the actual input image for the LVLM. Extensive experiments on various vison-language benchmarks verify the effectiveness of our technique. For example, Attention Prompting on Image improves LLaVA-1.5 by 3.8% and 2.9% on MM-Vet and LLaVA-Wild benchmarks, respectively.

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="2409.17143")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 6 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yu-rp/apiprompting officialmentioned in papermentioned on GitHubjax 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

12 samples harvested; 8 ran; 2 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
3ran
4unverified

Licence: 2 of the 12 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 yu-rp/apiprompting. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

Conversation yu-rp/apiprompting/API/API_LLaVA/functions.py official repository ran MIT (permissive) · 8992e3094a2ca1d1 · report
KeywordsStoppingCriteria yu-rp/apiprompting/API/API_LLaVA/functions.py official repository ran MIT (permissive) · 2fe03dcbac95b31f · report
MaxNewTokensCriteria yu-rp/apiprompting/API/API_LLaVA/functions.py official repository ran MIT (permissive) · e1119b92480f0cdc · report
load_image yu-rp/apiprompting/API/API_LLaVA/functions.py official repository ran · honoured contract MIT (permissive) · 9b3c1cb391672ccb · report
load_images yu-rp/apiprompting/API/API_LLaVA/functions.py official repository ran · honoured contract MIT (permissive) · d5044bdde33c54c2 · report
process_images yu-rp/apiprompting/API/API_LLaVA/functions.py official repository ran · our draft was wrong MIT (permissive) · e8f3a2a1be36a4d7 · report
SeparatorStyle yu-rp/apiprompting/API/API_LLaVA/functions.py official repository unverified MIT (permissive) · 0c4ff52904c9e0e7 · report
StoppingCriteria yu-rp/apiprompting/API/API_LLaVA/functions.py official repository unverified MIT (permissive) · 724da83b5bf10219 · report
disable_torch_init yu-rp/apiprompting/API/API_LLaVA/functions.py official repository unverified MIT (permissive) · 62a88066e939d2c5 · report
getmask yu-rp/apiprompting/API/API_LLaVA/functions.py official repository unverified MIT (permissive) · 6565708bd99b9f3b · report
expand2square identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 592b3c1a88f93d7c · report
image_parser identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · a7bee88c1c7fd6a3 · report

Tasks

Visual Prompting

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionCLIPHeatmapSoftmax

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