SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.12930 · 2026

Rethinking VLMs for Image Forgery Detection and Localization

Jiequan Cui, Richang Hong, Shaofeng Guo

arXiv · PDF · Open in the Atlas

Code that ran

None of the 8 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (8 no recorded run), measured 2026-11-22; 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/2603.12930.json · badge: /api/ran/2603.12930.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
sha0fengGuo/IFDL-VLM community
Papers with Code archive
0 ran · 8 no recorded run
FunctionStatusWhere it lives
CLIPVisionTower Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("04deb19e388bd0b0")
How it ran

no invocation recorded.

CLIPVisionTowerS2 Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("11f0c6139b76738e")
How it ran

no invocation recorded.

LlavaConfig Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("18fc1382aeed437a")
How it ran

no invocation recorded.

LlavaLlamaForCausalLM Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("c5c93160b1124542")
How it ran

no invocation recorded.

LlavaLlamaModel Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("32df3264caf5e8fe")
How it ran

no invocation recorded.

LlavaMetaForCausalLM Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("ec9a2680c81d44c8")
How it ran

no invocation recorded.

LlavaMetaModel Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("0476644b7e89c2d5")
How it ran

no invocation recorded.

build_vision_tower Not yet run
unverified (harvested, no recorded run)
sha0fengGuo/IFDL-VLM/stage2/llava/model/language_model/llava_llama.py
code served (permissive licence) · get_code("b89f520c5cbc92b1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 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.

FunctionAlso present inEarliest-datedOthers named
LlavaLlamaModel
brick of this paper's assembly: model
13 other papers
11 dated earlier, 2 the same month · 3 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2404.05673 (2024-04)
CoReS: Orchestrating the Dance of Reasoning and Segmentation
2405.14974 (2024-05)
LOVA 3 : Learning to Visual Question Answering, Asking and Assessment
and 10 more not named here
build_vision_tower
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 2 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2406.20095 (2024-06)
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
2502.13508 (2025-02)
VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
and 1 more not named here
CLIPVisionTowerS2
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 2 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2406.20095 (2024-06)
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
2502.13508 (2025-02)
VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
LlavaMetaModel
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
2304.08485 (2023-04)
Visual Instruction Tuning
2406.20095 (2024-06)
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

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

With the rapid rise of Artificial Intelligence Generated Content (AIGC), image manipulation has become increasingly accessible, posing significant challenges for image forgery detection and localization (IFDL). In this paper, we study how to fully leverage vision-language models (VLMs) to assist the IFDL task. In particular, we observe that priors from VLMs hardly benefit the detection and localization performance and even have negative effects due to their inherent biases toward semantic plausibility rather than authenticity. Additionally, the location masks explicitly encode the forgery concepts, which can serve as extra priors for VLMs to ease their training optimization, thus enhancing the interpretability of detection and localization results. Building on these findings, we propose a new IFDL pipeline -IFDL-VLM. To demonstrate the effectiveness of our method, we conduct experiments on 9 popular benchmarks and assess the model performance under both settings of in-domain and cross-dataset generalization. The experimental results show that we consistently achieve new state-of-the-art performance in detection, localization, and interpretability. Code is available at https://github.com/sha0fengGuo/IFDL-VLM.

For agents

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

get_harvested_code_for_paper("2603.12930")
get_code_for_paper("2603.12930")
have("2603.12930")

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

curl https://syntology.ai/api/ran/2603.12930.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.12930.svg)](https://syntology.ai/paper/2603.12930)

Connect an agent — have() is free.