PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment | Paper Citation Record

Observation 32d9ab13-412e-44e9-91da-95889faf2b66 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.127861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0429e9e-e10e-4dc9-b726-c6df87f5c87d · outbound

This paper cites Image hijacks: Adversarial images can control generative models at runtime, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Image hijacks: Adversarial images can control generative models at runtime, 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.949694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a6b154bb-a044-4e52-9bdb-6e121b68aaf8 · outbound

This paper cites Introducing our multimodal models, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Introducing our multimodal models, 2023

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.937976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fc67f042-bb33-46d2-ba9f-4abd0af7faf9 · outbound

This paper cites Image safeguarding: Reasoning with conditional vision language model and obfuscating unsafe content counterfactually, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Image safeguarding: Reasoning with conditional vision language model and obfuscating unsafe content counterfactually, 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.925201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 23467f4c-1b7a-44f7-b46d-b0f62c61e11d · outbound

This paper cites Honeybee: Locality-enhanced projector for multimodal llm.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Honeybee: Locality-enhanced projector for multimodal llm

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.913698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 72440e1a-9935-4c87-8042-b190e1378edd · outbound

This paper cites Antifakeprompt: Prompt-tuned vision-language models are fake image detectors, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Antifakeprompt: Prompt-tuned vision-language models are fake image detectors, 2023

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.901712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 384f5638-c27c-4d99-804d-2d910caefcd1 · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.154314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 516ed2bc-7c04-4040-93ae-a7438301a33a · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.159094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4db07976-ba95-4c85-bf39-62f6d1e6375e · outbound

This paper cites Cogview: Mastering text-to-image generation via transformers.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Cogview: Mastering text-to-image generation via transformers

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.889327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8c68a258-628a-404e-9980-cc0ac6a8e8af · outbound

This paper cites InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.168107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82475f71-b3da-4f34-8dd4-0b3969378aae · outbound

This paper cites Glm: General language model pretraining with autoregressive blank infilling.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Glm: General language model pretraining with autoregressive blank infilling

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.876353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9fbfbe23-38ba-4fc4-b04b-bd5d62b480c1 · outbound

This paper cites Mme: A comprehen- sive evaluation benchmark for multimodal large language models, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Mme: A comprehen- sive evaluation benchmark for multimodal large language models, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.864604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9f88201e-ac5f-4c0a-9473-c8ed226d9a55 · outbound

This paper cites Inducing high energy-latency of large vision-language models with verbose images, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Inducing high energy-latency of large vision-language models with verbose images, 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.853154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 54304045-3415-40dd-a318-4255ee4feecb · outbound

This paper cites Fig- step: Jailbreaking large vision-language models via typo- graphic visual prompts, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Fig- step: Jailbreaking large vision-language models via typo- graphic visual prompts, 2023

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.840982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aea55f20-49c2-4dca-bc3c-7819b1cb748c · outbound

This paper cites OneLLM: One Framework to Align All Modalities with Language.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment OneLLM: One Framework to Align All Modalities with Language

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.186515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4158e1b0-d3f4-484f-a553-a10d97d131ab · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.828033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e8917f62-199c-4d5e-a97b-0054c61feb2a · outbound

This paper cites Nsfw data scraper.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Nsfw data scraper

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.815309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b48f14e9-1907-4d64-80d8-83f050a9d852 · outbound

This paper cites Concept bottleneck models.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Concept bottleneck models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.803049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 36d6e535-6381-4184-9ed1-bbba99defa90 · outbound

This paper cites A hierarchical approach for generating descriptive image paragraphs, 2017.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment A hierarchical approach for generating descriptive image paragraphs, 2017

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.790177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d651c935-b420-4915-a41c-e90ce28adeed · outbound

This paper cites SEED-Bench-2: Benchmarking Multimodal Large Language Models.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment SEED-Bench-2: Benchmarking Multimodal Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.209278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da9cca8-247f-47a5-807c-394543fc7752 · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.214041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1af47637-f9f6-44a6-b7f7-cbc4b68ff7dd · outbound

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

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Blip: Bootstrapping language-image pre-training for unified vision- language understanding and generation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.218280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f1abdc0-db2c-47be-aa7d-21d262855cdd · outbound

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

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.223174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd21dca-9a6a-47fb-9811-88397de0f38f · outbound

This paper cites Red teaming visual language models, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Red teaming visual language models, 2024

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.759080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2b5a6728-d3b1-4891-b394-d0747968a253 · outbound

This paper cites Vl-trojan: Mul- timodal instruction backdoor attacks against autoregressive visual language models, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Vl-trojan: Mul- timodal instruction backdoor attacks against autoregressive visual language models, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.746772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cb154169-5e40-4037-86cf-df5d4bb7bc15 · outbound

This paper cites Microsoft coco: Common objects in context.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Microsoft coco: Common objects in context

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.236310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2f33554-7af2-4bb3-9c76-b3567be80bfe · outbound

This paper cites Improved baselines with visual instruction tuning, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Improved baselines with visual instruction tuning, 2023

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.726907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e7d6b7e4-f1e5-4632-ad78-443b1bf4867a · outbound

This paper cites Visual instruction tuning, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Visual instruction tuning, 2023

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.713400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 07a51b75-5fc9-4e81-97af-1374d39169f6 · outbound

This paper cites Llava-next: Improved reason- ing, ocr, and world knowledge, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Llava-next: Improved reason- ing, ocr, and world knowledge, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.249485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eeea764-5569-42c9-96b9-9964801e3ba9 · outbound

This paper cites Visual instruction tuning.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Visual instruction tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.253243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a749d1e-df2a-4729-8ad2-43143ac3e85e · outbound

This paper cites Mm-safetybench: A benchmark for safety evaluation of multimodal large language models, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Mm-safetybench: A benchmark for safety evaluation of multimodal large language models, 2024

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.686040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 21b551e1-6c26-4d88-b361-fa71c5e1742b · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player?, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Mmbench: Is your multi-modal model an all-around player?, 2023

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.672265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 745a8f39-1d37-4cc8-a75d-73379872db57 · outbound

This paper cites Deep learning face attributes in the wild, 2015.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Deep learning face attributes in the wild, 2015

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.658621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 18ad0113-9428-4918-bb47-c6671d5f068a · outbound

This paper cites Interpretability Beyond Classification Output: Semantic Bottleneck Networks.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Interpretability Beyond Classification Output: Semantic Bottleneck Networks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.267678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83cd5ba9-4f87-48a2-8902-e80d08d2aa05 · outbound

This paper cites Stable bias: Evaluating societal representa- tions in diffusion models.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Stable bias: Evaluating societal representa- tions in diffusion models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.646418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7b50ee66-87f1-4bc2-918a-81570f5edf0c · outbound

This paper cites Gpt-4 technical report, 2024.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Gpt-4 technical report, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.275572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7d1738d-f720-400f-9c35-38ef544e26a0 · outbound

This paper cites llama3-vision-alpha.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment llama3-vision-alpha

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.626757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 85d538d1-28a7-42c8-99d5-2825c96c3f4f · outbound

This paper cites Learning transferable visual models from natural language supervision, 2021.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Learning transferable visual models from natural language supervision, 2021

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.282948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1184df5d-0577-4fd7-a415-3f016dd08efd · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.286362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3989e4ee-c4bd-4600-9925-a68e3db72797 · outbound

This paper cites How many unicorns are in this image? a safety evaluation benchmark for vision llms, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment How many unicorns are in this image? a safety evaluation benchmark for vision llms, 2023

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.608038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ac426aa2-3471-4d53-8eab-6f9773db2503 · outbound

This paper cites Towards understanding and detecting cyberbullying in real-world images.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Towards understanding and detecting cyberbullying in real-world images

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.596340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c669f67b-2509-4b8a-b24d-16cda2f2e17a · outbound

This paper cites Knowledge mining with scene text for fine-grained recognition, 2022.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Knowledge mining with scene text for fine-grained recognition, 2022

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.582483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e68a4896-fd60-4c66-bc0d-4fb006ef4ea3 · outbound

This paper cites Adversarial prompt tuning for vision-language models, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Adversarial prompt tuning for vision-language models, 2023

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.566740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9699e6de-3b32-43c8-89e5-9f4e5394b79a · outbound

This paper cites A mutation-based method for multi-modal jailbreaking attack detection, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment A mutation-based method for multi-modal jailbreaking attack detection, 2023

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.550558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 12984441-25fb-4e15-86b5-f7b0491619dd · outbound

This paper cites Meta-Transformer: A Unified Framework for Multimodal Learning.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Meta-Transformer: A Unified Framework for Multimodal Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T18:29:33.316995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf18c04-9c75-459b-9f2f-c8cb34a113b7 · outbound

This paper cites Privacyalert: A dataset for image privacy prediction.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Privacyalert: A dataset for image privacy prediction

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.536365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bddfeaf5-f538-465d-a979-3561447de2d4 · outbound

This paper cites On evaluating adversarial robustness of large vision-language models, 2023.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment On evaluating adversarial robustness of large vision-language models, 2023

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.520984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 098cacae-68eb-49fe-875d-ea5afa1a7156 · outbound

This paper cites Manning, Christopher Potts, and Danqi Chen.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment Manning, Christopher Potts, and Danqi Chen

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.507548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 50236ac9-7aec-4818-a11d-6968cc81379e · outbound

This paper cites A" and "B.

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment A" and "B

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:29:33.494338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers