Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models | Paper Citation Record

Observation 2929c61c-93ba-409e-8e8c-d0ed81bbf05f · outbound

This paper cites Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.319499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a33842c0-3303-4d4c-a2a8-a2d55d41bdc4 · outbound

This paper cites Food-101–mining discriminative components with random forests.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Food-101–mining discriminative components with random forests

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.937712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc965721-a993-4505-b3e3-21f4e0da1531 · outbound

This paper cites Towards evaluating the robustness of neural networks.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Towards evaluating the robustness of neural networks

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.893282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 76149d10-dbf5-47af-b4c0-0398366df46c · outbound

This paper cites Describing textures in the wild.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Describing textures in the wild

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.888777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7909f247-139b-46bf-9845-9eae531e4fbc · outbound

This paper cites An analysis of single-layer networks in unsupervised feature learning.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models An analysis of single-layer networks in unsupervised feature learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.926855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7945fd93-7dec-4d90-b244-40349ebd9bfc · outbound

This paper cites Reliable evaluation of adversarial robustness with an ensemble of diverse parameter- free attacks.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Reliable evaluation of adversarial robustness with an ensemble of diverse parameter- free attacks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.919546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9370282a-b023-4bf1-99b7-6fca481cf447 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Imagenet: A large-scale hierarchical image database

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.888342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f83d97b4-737d-4213-9b47-7dbec88cd4c5 · outbound

This paper cites Improving zero-shot adversarial robustness in vision-language models by closed- form alignment of adversarial path simplices.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Improving zero-shot adversarial robustness in vision-language models by closed- form alignment of adversarial path simplices

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.911533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4dd87eee-9bf3-421a-9854-be2feb44a8a0 · outbound

This paper cites One-shot learn- ing of object categories.IEEE transactions on pattern analy- sis and machine intelligence, 28(4):594–611.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models One-shot learn- ing of object categories.IEEE transactions on pattern analy- sis and machine intelligence, 28(4):594–611

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.940244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c2db4f7-56c2-4181-8f62-091a5d035d6d · outbound

This paper cites Finetune like you pretrain: Improved finetuning of zero-shot vision models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Finetune like you pretrain: Improved finetuning of zero-shot vision models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.935401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a47e700c-627c-45cb-b119-bc066ba1d11f · outbound

This paper cites Caltech-256 object category dataset.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Caltech-256 object category dataset

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.924381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0bc12d05-d6a1-46e3-8f2a-804b843b5168 · outbound

This paper cites Deep residual learning for image recognition.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Deep residual learning for image recognition

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.921861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc1a1b5f-2a9f-4155-a89d-8d1f161933e5 · outbound

This paper cites an unresolved cited work.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-05-17T17:41:59.952320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7b724c9e-65bb-4824-8c6d-cb9dee23ce44 · outbound

This paper cites The many faces of robust- ness: A critical analysis of out-of-distribution generalization.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models The many faces of robust- ness: A critical analysis of out-of-distribution generalization

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.962807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5fbec500-ecbf-4187-a337-d3bb0c73fc53 · outbound

This paper cites Natural adversarial examples.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Natural adversarial examples

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.959817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ad3dd509-422c-402d-b627-2f1a961f71e4 · outbound

This paper cites Scaling up visual and vision-language representation learning with noisy text supervision.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Scaling up visual and vision-language representation learning with noisy text supervision

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.237954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a58ad780-5977-4349-8301-85979d5321dc · outbound

This paper cites 3d object representations for fine-grained categorization.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models 3d object representations for fine-grained categorization

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.242786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5e886f48-c022-4f0e-b2da-2199df593ef1 · outbound

This paper cites Learning multiple layers of features from tiny images.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Learning multiple layers of features from tiny images

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.246925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8634692d-f0c0-4c31-9a32-82208489dea2 · outbound

This paper cites Im- agenet classification with deep convolutional neural networks.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Im- agenet classification with deep convolutional neural networks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.267889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 14d9ee75-a15c-45d9-856c-05b37b5ac586 · outbound

This paper cites Fine-tuning can distort pre- trained features and underperform out-of-distribution.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Fine-tuning can distort pre- trained features and underperform out-of-distribution

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.212337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b7c798a-471c-4d5d-a3f3-bbcf6e849b3f · outbound

This paper cites Tiny imagenet visual recognition challenge.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Tiny imagenet visual recognition challenge

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.902026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c9d99b58-cae0-4cfb-94fc-91c9840d69b7 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision- language understanding and generation.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Blip: Bootstrapping language-image pre-training for unified vision- language understanding and generation

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.203875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 89f0c6bc-2eca-4ec6-a658-189f5f06ae87 · outbound

This paper cites Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.208598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation baa05a66-2577-4a79-a1c6-dbca5dcb86b6 · outbound

This paper cites One prompt word is enough to boost adversarial robustness for pre-trained vision-language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models One prompt word is enough to boost adversarial robustness for pre-trained vision-language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.216043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 86ec9475-85cb-4f2a-9ef0-6c9a2a48d23e · outbound

This paper cites Defense against adversarial attacks using high-level representation guided denoiser.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Defense against adversarial attacks using high-level representation guided denoiser

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.230348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a39425e8-d50e-4341-aecd-0b84f727b89f · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.188310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a495e399-8c10-42c7-93c8-f1b42b2aa78e · outbound

This paper cites Image segmentation us- ing text and image prompts.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Image segmentation us- ing text and image prompts

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.197784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6b8946b5-218e-4cf0-8914-d835d9626c6f · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Towards deep learning models resistant to adversarial attacks

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.180520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 35d7249c-3cb3-48e5-852d-0a93e677d1f7 · outbound

This paper cites Fine-Grained Visual Classification of Aircraft.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Fine-Grained Visual Classification of Aircraft

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:41:07.065951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6a41a3f0-ac6e-4aed-ad2d-f82cb88ecb99 · outbound

This paper cites Understanding zero-shot adversarial robust- ness for large-scale models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Understanding zero-shot adversarial robust- ness for large-scale models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.183993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 606861d3-d388-4025-9421-42baf6a46448 · outbound

This paper cites Context-aware robust fine-tuning.Interna- tional Journal of Computer Vision, 132(5):1685–1700.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Context-aware robust fine-tuning.Interna- tional Journal of Computer Vision, 132(5):1685–1700

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.191341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fca7e8d7-16f2-44fb-b596-0d0f137a4d96 · outbound

This paper cites Lipsum-FT: Ro- bust fine-tuning of zero-shot models using random text guid- ance.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Lipsum-FT: Ro- bust fine-tuning of zero-shot models using random text guid- ance

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.194806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b87682ef-dc13-4d4e-846e-7c48119ff211 · outbound

This paper cites Automated flower classification over a large number of classes.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Automated flower classification over a large number of classes

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.260230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1c799649-2b77-4c7b-abdc-6a4b562df6bb · outbound

This paper cites Towards calibrated robust fine-tuning of vision-language models.Advances in Neural Information Processing Systems, 37:12677–12707.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Towards calibrated robust fine-tuning of vision-language models.Advances in Neural Information Processing Systems, 37:12677–12707

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.308958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ebeb9347-f286-4ed1-8386-92292f416404 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Representation Learning with Contrastive Predictive Coding

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:31:05.888640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a56f1732-8ef1-4391-916d-44c493040624 · outbound

This paper cites an unresolved cited work.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-05-17T17:41:59.954699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6ca7d8e9-86e8-423d-bfdc-ca60a745e197 · outbound

This paper cites Cats and dogs.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Cats and dogs

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.909181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d23d826a-709e-4c39-aaa6-a584cb9ce857 · outbound

This paper cites Styleclip: Text-driven manipulation of stylegan imagery.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Styleclip: Text-driven manipulation of stylegan imagery

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.908636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4dcf61f4-4b4f-4be4-89e0-55bb4af1f5ee · outbound

This paper cites What does a platypus look like? generating customized prompts for zero-shot image classification.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models What does a platypus look like? generating customized prompts for zero-shot image classification

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.278011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3a25adac-fbc0-49f2-b766-ac39d05f0db0 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Learning transferable visual models from natural language supervi- sion

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.295422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b2d0bec5-c14b-4e01-ae42-9ef282b82414 · outbound

This paper cites Overfitting in adver- sarially robust deep learning.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Overfitting in adver- sarially robust deep learning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.884912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 268d2882-1432-4c91-84fb-540fd09bb085 · outbound

This paper cites Im- proved zero-shot classification by adapting vlms with text descriptions.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Im- proved zero-shot classification by adapting vlms with text descriptions

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.945364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f177cb15-f50c-4258-91a7-17a5bc1d0ea3 · outbound

This paper cites Interpreting and analysing clip’s zero-shot image classification via mutual knowledge.Advances in Neural Information Processing Sys- tems, 37:39597–39631.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Interpreting and analysing clip’s zero-shot image classification via mutual knowledge.Advances in Neural Information Processing Sys- tems, 37:39597–39631

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.929790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 262a3b6c-ce41-404a-be5f-8457d752ba94 · outbound

This paper cites Robust clip: Unsupervised adversar- ial fine-tuning of vision embeddings for robust large vision- language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Robust clip: Unsupervised adversar- ial fine-tuning of vision embeddings for robust large vision- language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.873837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f4e3f746-b7fb-4492-8273-675eda0c8abd · outbound

This paper cites Laion-400m: Open dataset of clip-filtered 400 million image-text pairs.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Laion-400m: Open dataset of clip-filtered 400 million image-text pairs

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.300541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d731e7c0-cb8f-4888-8943-2ba02161a9c3 · outbound

This paper cites R-tpt: Improving adversarial robustness of vision-language mod- els through test-time prompt tuning.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models R-tpt: Improving adversarial robustness of vision-language mod- els through test-time prompt tuning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.226367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 565db654-3039-4bb5-b642-03ea5064bba3 · outbound

This paper cites Intriguing properties of neural networks.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Intriguing properties of neural networks

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.282577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 75c4081a-6126-4fe1-b8be-11296fdf9a64 · outbound

This paper cites On the zero-shot adversarial robustness of vision-language models: A truly zero-shot and training-free approach.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models On the zero-shot adversarial robustness of vision-language models: A truly zero-shot and training-free approach

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.885428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 91d54fe2-7df3-40db-beee-ad7e2e3bb2eb · outbound

This paper cites Learning robust global representations by penalizing local predictive power.Advances in neural information processing systems, 32.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Learning robust global representations by penalizing local predictive power.Advances in neural information processing systems, 32

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.323916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation df666936-8370-41bd-9086-f05ad16e1977 · outbound

This paper cites Declip: Decoupled learning for open- vocabulary dense perception.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Declip: Decoupled learning for open- vocabulary dense perception

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.957557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 417165b8-6c91-4e50-8c09-56f45de5cd16 · outbound

This paper cites Pre- trained model guided fine-tuning for zero-shot adversarial robustness.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Pre- trained model guided fine-tuning for zero-shot adversarial robustness

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.916843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b8241e98-7a17-4072-9228-9c35c5d237df · outbound

This paper cites Tapt: Test-time adversarial prompt tuning for robust inference in vision-language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Tapt: Test-time adversarial prompt tuning for robust inference in vision-language models

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.947773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b44f8bcb-e0fc-4d78-a025-a209ac946acf · outbound

This paper cites Quality text, robust vision: The role of language in enhancing visual robustness of vision-language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Quality text, robust vision: The role of language in enhancing visual robustness of vision-language models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.965138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d10b628d-94a5-4022-8db0-e29d14d186fe · outbound

This paper cites Sun database: Large-scale scene recog- nition from abbey to zoo.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Sun database: Large-scale scene recog- nition from abbey to zoo

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.286734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd272cff-cba1-4529-a86f-7246b0c109b3 · outbound

This paper cites Clip is strong enough to fight back: Test-time counterattacks towards zero- shot adversarial robustness of clip.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Clip is strong enough to fight back: Test-time counterattacks towards zero- shot adversarial robustness of clip

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.234241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7426ec7c-e0a2-4e0b-a54a-f4e9d455b511 · outbound

This paper cites Text-guided attention is all you need for zero-shot robustness in vision- language models.Advances in Neural Information Processing Systems, 37:96424–96448.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Text-guided attention is all you need for zero-shot robustness in vision- language models.Advances in Neural Information Processing Systems, 37:96424–96448

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.222618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 760b5bb3-733e-4246-90bf-3df19184e925 · outbound

This paper cites Theoretically principled trade-off between robustness and accuracy.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Theoretically principled trade-off between robustness and accuracy

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.200796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ead92761-baff-4e21-91ed-2d4e41ea20ad · outbound

This paper cites Adversarial prompt tuning for vision-language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Adversarial prompt tuning for vision-language models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.263829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c9b4bfb-4b6c-4e7c-ba9b-5716e3799cf6 · outbound

This paper cites CLIPure: Purification in latent space via CLIP for adversarially robust zero-shot classification.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models CLIPure: Purification in latent space via CLIP for adversarially robust zero-shot classification

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.314155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0ea6e37d-4410-4be9-9759-372aab8d6531 · outbound

This paper cites Point- clip: Point cloud understanding by clip.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Point- clip: Point cloud understanding by clip

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.932825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 507f72d2-4c98-4e7b-88cb-c71bdffb41e4 · outbound

This paper cites On evaluating adversarial robustness of large vision-language models.Ad- vances in Neural Information Processing Systems, 36:54111– 54138.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models On evaluating adversarial robustness of large vision-language models.Ad- vances in Neural Information Processing Systems, 36:54111– 54138

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.914162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8b8a02df-649f-490c-9bf9-39a81a0e70bc · outbound

This paper cites Regionclip: Region-based language- image pretraining.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Regionclip: Region-based language- image pretraining

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.881953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9b6b2ca5-cc1b-4a31-816b-c939ff65b8ed · outbound

This paper cites Conditional prompt learning for vision-language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Conditional prompt learning for vision-language models

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.967213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2e7aabab-c560-4374-b7d3-3fb76ced370c · outbound

This paper cites Learning to prompt for vision-language models.Interna- tional Journal of Computer Vision, 130(9):2337–2348.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Learning to prompt for vision-language models.Interna- tional Journal of Computer Vision, 130(9):2337–2348

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.942578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5ed3e947-31f9-4691-890f-88eab8cf079a · outbound

This paper cites Few-shot adversarial prompt learning on vision-language models.Advances in Neural Information Processing Systems, 37:3122–3156.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Few-shot adversarial prompt learning on vision-language models.Advances in Neural Information Processing Systems, 37:3122–3156

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:41:59.898957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 60802fe9-1143-436b-9d99-3efe2b593a72 · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large language models.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Minigpt-4: Enhancing vision-language understanding with advanced large language models

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.254430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c60f7ccc-6d42-4e5f-824f-4976c47e2c04 · outbound

This paper cites an unresolved cited work.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-05-17T17:40:03.250680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 53d73022-d57b-41b0-8714-b74cadc4e6e1 · outbound

This paper cites an unresolved cited work.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-05-17T17:40:03.290694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0603ecfd-e201-46b6-b210-0978bc633f82 · outbound

This paper cites Robustness under Higher Attack Budgets We report the full tables of robustness evaluated under the attack strength of ϵ= 2/255 and ϵ= 4/255 in Tab.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Robustness under Higher Attack Budgets We report the full tables of robustness evaluated under the attack strength of ϵ= 2/255 and ϵ= 4/255 in Tab

Reference 69

Resolution: malformed identifier; arxiv_id, observed 2026-05-11T09:31:05.879592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 62dcbf51-e7ad-4e57-8c56-4bd74941161e · outbound

This paper cites This paradigm is reasonable in the sense that the fine- tuned CLIP is to be deployed in downstream classification datasets.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models This paradigm is reasonable in the sense that the fine- tuned CLIP is to be deployed in downstream classification datasets

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T17:40:03.304298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0a1bacac-8d7d-4ac3-95c8-3e858318cfed · outbound

This paper cites an unresolved cited work.

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-05-17T17:41:59.950100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers