SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.19956 · ICML · 2026

Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models

Xiu-Shen Wei, Yijun Wang, Jia-Wei Hai

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 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/2605.19956.json · badge: /api/ran/2605.19956.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
SEU-VIPGroup/A-TPT canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SEU-VIPGroup/A-TPT/utils/tools.py
pointer only (licence: NONE) · get_code("b0f936d4d6ae3b8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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. A run is recorded.

get_pairs Ran
ran; our contract draft was wrong, not the code
SEU-VIPGroup/A-TPT/clip/simple_tokenizer.py
pointer only (licence: NONE) · get_code("d919ae32e5e4e616")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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. A run is recorded.

validate Ran
ran, honoured the contract we drafted
SEU-VIPGroup/A-TPT/utils/tools.py
pointer only (licence: NONE) · get_code("1ca27622f8ca45e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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. A run is recorded.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
SEU-VIPGroup/A-TPT/clip/simple_tokenizer.py
pointer only (licence: NONE); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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. A run is recorded.

wrapper_method Ran
ran; our contract draft was wrong, not the code
SEU-VIPGroup/A-TPT/torchattacks/attack.py
pointer only (licence: NONE); the stored copy get_code serves, from nilspwalter/the-uncanny-valley, is pointer only (licence: NOASSERTION) · get_code("9b45cb80d93fe980")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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. A run is recorded.

build_model Not yet run
unverified (harvested, no recorded run)
SEU-VIPGroup/A-TPT/clip/model.py
pointer only (licence: NONE) · get_code("ce030f573ae70489")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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.

differential_evolution Not yet run
unverified (harvested, no recorded run)
SEU-VIPGroup/A-TPT/torchattacks/attacks/_differential_evolution.py
pointer only (licence: NONE) · get_code("c4f7c480f2fa7ba0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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.

load Not yet run
unverified (harvested, no recorded run)
SEU-VIPGroup/A-TPT/clip/clip.py
pointer only (licence: NONE) · get_code("db594353b8cf5c9f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SEU-VIPGroup/A-TPT 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 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, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 3 the same month, 3 later) and 1 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
get_pairs 258 other papers
248 dated earlier, 3 the same month, 6 later, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
223 dated earlier, 3 the same month, 4 later, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
accuracy 116 other papers
111 dated earlier, 2 the same month, 3 later · 8 only as an assembly brick
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1610.05820 (2016-10)
Membership Inference Attacks Against Machine Learning Models
1905.03696 (2019-05)
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
and 113 more not named here
build_model 9 other papers
9 dated earlier
2305.18010 (2023-05)
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
2311.15243 (2023-11)
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
2401.15657 (2024-01)
Data-Free Generalized Zero-Shot Learning
and 6 more not named here
wrapper_method 6 other papers
6 dated earlier
2310.18274 (2023-10)
LipSim: A Provably Robust Perceptual Similarity Metric
2401.16352 (2024-01)
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
2402.02309 (2024-02)
Jailbreaking Attack against Multimodal Large Language Model
and 3 more not named here
validate 2 other papers
2 dated earlier
2403.14119 (2024-03)
C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
2403.17589 (2024-03)
Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
differential_evolution 1 other paper
1 dated earlier
2010.01950 (2020-10)
Torchattacks: A PyTorch Repository for Adversarial Attacks

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

Vision-Language Models (VLMs), such as CLIP, have achieved significant zero-shot performance on downstream tasks with various fine-tuning adaptation methods. However, recent studies have proven that adversarial attacks can significantly degrade the inference ability of VLMs, posing substantial risks to their practical applications. Prevalent test-time adaptation methods typically rely on multi-view augmentation to implement various fine-tuning strategies, which struggle to identify semantic information and are prone to destroying discriminative regions in fine-grained scenarios. To address these limitations, we propose Attention-Guided Test-Time Prompt Tuning (A-TPT), a semantics-preserving method designed for test-time adaptation. We first refine the gradient attention rollout mechanism to identify semantically meaningful regions surviving under adversarial attacks. Furthermore, we leverage them to guide the spatially varying augmentation intensities and multi-view ensemble for prompt tuning and inference. Extensive experiments demonstrate that A-TPT outperforms existing test-time adaptation methods on both adversarial and clean data. Codes are available at https: //github.com/SEU-VIPGroup/A-TPT.

For agents

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

get_harvested_code_for_paper("2605.19956")
get_code_for_paper("2605.19956")
have("2605.19956")

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

curl https://syntology.ai/api/ran/2605.19956.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.19956.svg)](https://syntology.ai/paper/2605.19956)

Connect an agent — have() is free.