Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities | Paper Citation Record

Observation de479335-37c3-4d7c-be41-782cef9fa42e · outbound

This paper cites https://huggingface.co/deepseek-ai/ 13 DeepSeek-R1.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https://huggingface.co/deepseek-ai/ 13 DeepSeek-R1

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.236155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3845f66e-d594-4ce7-b367-fd4bae1e3fcd · outbound

This paper cites https://openai.com/index/gpt-4-1/.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https://openai.com/index/gpt-4-1/

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.213411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2705751e-6dbd-4d2d-bf6d-25123558ba53 · outbound

This paper cites https://openai.com/research/gpt-4v- system-card.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https://openai.com/research/gpt-4v- system-card

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.185507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 62008d21-bb05-4e6a-b5c5-b5a8b18aa477 · outbound

This paper cites https://huggingface.co/datasets/laion/ laion2B-en.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https://huggingface.co/datasets/laion/ laion2B-en

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.160262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dfb1bc55-ccb3-4378-a25f-0c5bbf95b529 · outbound

This paper cites https: //academictorrents.com/details/ 1cda9427784a6b77809f657e772814dc766b69f5.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https: //academictorrents.com/details/ 1cda9427784a6b77809f657e772814dc766b69f5

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.132459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6ac9360b-cd54-4c35-bb10-ff6067519a5a · outbound

This paper cites https://web.archive.org/web/ 20220406151527/https://labs.openai.com/policies/ content-policy.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https://web.archive.org/web/ 20220406151527/https://labs.openai.com/policies/ content-policy

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.106730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 83110e28-ebbf-498a-82ea-25f343e7677a · outbound

This paper cites https://openai.com/o1/.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https://openai.com/o1/

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.085062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e450028e-a585-4add-9526-52bf0d21a505 · outbound

This paper cites https://osf.io/2rqad/.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities https://osf.io/2rqad/

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.057871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 18bdc356-6edd-44ff-8389-a227cc205a27 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.156208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47a09fa3-174c-42c8-ba3d-c067bf6da595 · outbound

This paper cites Designing Neural Network Architectures using Rein- forcement Learning.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Designing Neural Network Architectures using Rein- forcement Learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.036711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2c0199ff-0443-4701-9516-ef4c6ce22a61 · outbound

This paper cites Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:36.019184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f4895b71-2732-4461-b5bc-b051b20bc177 · outbound

This paper cites InternLM2 Technical Report.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities InternLM2 Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.166750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abe12a9e-b13f-4f56-bd0c-71d1e175db75 · outbound

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

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.170826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd2e3fcc-0580-4157-94c0-15377cc20100 · outbound

This paper cites Christiano, Jan Leike, Tom B.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Christiano, Jan Leike, Tom B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.175318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86f736ee-9392-4189-ae26-0823d40af63c · outbound

This paper cites an unresolved cited work.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:21:35.997267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e83941c-494d-48dd-8b6b-bae0b4bfcd27 · outbound

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

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities ImageNet: A large-scale hierarchical image database

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.984232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 46b7d000-77e8-41a7-a883-caccc8755ba0 · outbound

This paper cites ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.186888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c217dcee-af51-45ad-ac57-61bb58e5735b · outbound

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

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.190481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1936df79-e57c-42bc-a82a-46f309452a11 · outbound

This paper cites Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.194359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23b65e5f-de48-450a-883e-a0c63e09addf · outbound

This paper cites Fleiss’ kappa statistic without paradoxes.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Fleiss’ kappa statistic without paradoxes

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.198149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de8e157-ab5d-4a0c-aaf3-bb59dcb0aaa9 · outbound

This paper cites Measuring Nominal Scale Agreement Among Many Raters.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Measuring Nominal Scale Agreement Among Many Raters

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.202068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d52d7e1-7c04-4e59-b9d1-d849e87e2b27 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.205357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d549b25a-4dac-4f19-9750-9debf0272fd8 · outbound

This paper cites FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.208807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc3de447-b1b9-46ac-9c95-d0bd99d06b01 · outbound

This paper cites Kwok, and Yu Zhang.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Kwok, and Yu Zhang

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.958067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dd154da8-3727-42be-82e9-396a68385a9b · outbound

This paper cites Moderating Illicit Online Image Promo- tion for Unsafe User-Generated Content Games Using Large Vision-Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Moderating Illicit Online Image Promo- tion for Unsafe User-Generated Content Games Using Large Vision-Language Models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.947447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fafedff1-86aa-4ec7-a2ca-2309d30b53ac · outbound

This paper cites LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.219871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe8159af-8419-41c0-b7a7-1a5e90c57591 · outbound

This paper cites Glass, Akash Srivastava, and Pulkit Agrawal.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Glass, Akash Srivastava, and Pulkit Agrawal

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.936855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c9250c89-11de-428e-a8f1-c7800e71b84c · outbound

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

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.925456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a18f95d8-9b31-4586-a393-65111424bd3d · outbound

This paper cites Deep Reinforcement Learning for Di- alogue Generation.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Deep Reinforcement Learning for Di- alogue Generation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.915021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 438ccd36-c875-413f-a23b-e4f14297bd45 · outbound

This paper cites BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.235072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197ee628-b76b-4860-9504-86827db0aa01 · outbound

This paper cites Silkie: Preference Distillation for Large Visual Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Silkie: Preference Distillation for Large Visual Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.238949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bea15e90-d2cf-4593-adcf-9b1e5939ef22 · outbound

This paper cites Red Teaming Visual Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Red Teaming Visual Language Models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.904973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9a707ee9-00d6-4970-a3c2-35751f12fba4 · outbound

This paper cites GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.246231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e7297ca-769d-49f1-9d06-003aa41fe1be · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.893067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b1f2be79-c6f2-4023-bd69-e7bf4bd24fca · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Improved Baselines with Visual Instruction Tuning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.254512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fca06dda-adac-42f5-a31c-5adfe6756e1f · outbound

This paper cites Visual Instruction Tuning.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Visual Instruction Tuning

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.880351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2faa3e67-f4e6-46ee-85f4-9463ca6e7bcf · outbound

This paper cites Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.262536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e894b5c-b5e4-4f10-99a8-b270c72bb9e9 · outbound

This paper cites MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.869284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f03aac4f-842b-40ae-84fa-8b4b78a6425d · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.269179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3acacffc-bf8e-4d23-8f7e-673730b424ca · outbound

This paper cites Safety Alignment for Vision Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Safety Alignment for Vision Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.272675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a56f1111-94f5-472d-912c-ff112a1ca5a0 · outbound

This paper cites From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Mod- els.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities From Meme to Threat: On the Hateful Meme Understanding and Induced Hateful Content Generation in Open-Source Vision Language Mod- els

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.858852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4e622c8d-4a8c-4177-b087-afdfaef88c04 · outbound

This paper cites an unresolved cited work.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:21:35.847374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50bc509b-1ddb-4157-850f-f19e99d996b9 · outbound

This paper cites GPT-4 Technical Report.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities GPT-4 Technical Report

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.282837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6b75b0-5afb-4771-8d0d-446cfaead8b1 · outbound

This paper cites Efros, and Trevor Darrell.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Efros, and Trevor Darrell

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.837911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b1632b72-81db-4f0f-861a-6e8f9ece354b · outbound

This paper cites Visual Adversarial Examples Jailbreak Aligned Large Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.290281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f67fa2e5-384f-4cc9-a0f4-9d271e4a1de4 · outbound

This paper cites On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learn- ing.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learn- ing

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.828089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 011ea5f8-e16b-47fa-8bdd-fe77222e103f · outbound

This paper cites Unsafe Diffusion: On the Gen- eration of Unsafe Images and Hateful Memes From Text-To- Image Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Unsafe Diffusion: On the Gen- eration of Unsafe Images and Hateful Memes From Text-To- Image Models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.814657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1aa2458a-4eb7-4ac5-8c6b-f652f18bcc17 · outbound

This paper cites UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.300886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da40a24f-6f79-47c9-8e59-5fcf662f07cf · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Learning Transferable Visual Models From Natural Language Supervision

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.802346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 786f692e-4762-405e-8cda-7178cee67106 · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Manning, Stefano Ermon, and Chelsea Finn

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.789689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c5e82af-a94f-420a-b7a3-d07d305c1978 · outbound

This paper cites Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.311066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35be7c9-a6dd-4902-bcbc-86d09efac4a2 · outbound

This paper cites Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.315436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb4527a-5233-4b6a-b959-237078f85288 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Proximal Policy Optimization Algorithms

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.319076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197ef339-8d22-4290-808f-3a0a717836ca · outbound

This paper cites HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Cam- paigns.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Cam- paigns

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.322406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bfa66ed-6201-4f70-81cc-6ee2ef44e5e6 · outbound

This paper cites Assessment of Multimodal Large Language Models in Alignment with Human Values.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Assessment of Multimodal Large Language Models in Alignment with Human Values

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.326106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f67551d3-b7b4-40ee-bf94-4af4e4236075 · outbound

This paper cites an unresolved cited work.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:21:35.768524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fbd7e762-aab8-4f8d-a33f-cc4ad88a93c9 · outbound

This paper cites Align- ing Large Multimodal Models with Factually Augmented RLHF.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Align- ing Large Multimodal Models with Factually Augmented RLHF

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.757327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cfb9e0df-b385-4594-a38f-b907dc1c8ccb · outbound

This paper cites Vicuna: An Open-Source Chatbot Impress- ing GPT-4 with 90%* ChatGPT Quality.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Vicuna: An Open-Source Chatbot Impress- ing GPT-4 with 90%* ChatGPT Quality

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.745048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d5218bbb-8a69-4f89-a888-3092290f110f · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.340516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e60edac-3f2c-4201-8a5d-126e1d465497 · outbound

This paper cites Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.344438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c365a7-aa0e-4201-a726-517095b23028 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities CogVLM: Visual Expert for Pretrained Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.347771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b74250c5-fcb7-4e9e-bac2-d0389d5afa0d · outbound

This paper cites RL-VLM-F: Rein- forcement Learning from Vision Language Foundation Model Feedback.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities RL-VLM-F: Rein- forcement Learning from Vision Language Foundation Model Feedback

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.733568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b90fd3dc-1854-450a-b2cc-e1efdc81e7d4 · outbound

This paper cites The Perfect Blend: Redefining RLHF with Mixture of Judges.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities The Perfect Blend: Redefining RLHF with Mixture of Judges

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.355204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51af121b-4754-4101-9dfd-43e10568370e · outbound

This paper cites Qwen2 Technical Report.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Qwen2 Technical Report

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.359327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be4f0882-b600-49f2-afe0-ca71eed6ddc9 · outbound

This paper cites Bridge the Modality and Capability Gaps in Vision-Language Model Selection.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Bridge the Modality and Capability Gaps in Vision-Language Model Selection

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:21:35.449506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2118bebf-d9d8-4211-99e4-9b19d984e47d · outbound

This paper cites RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-Grained Correctional Human Feedback.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-Grained Correctional Human Feedback

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.721254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ffc2c45d-0465-46fb-a516-7373399e78f1 · outbound

This paper cites SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.371849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b83a515-e482-4667-93b7-ce63f42bb000 · outbound

This paper cites Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.375340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 641d9c1f-33ee-4821-a3c0-9a6db5d9a12c · outbound

This paper cites On Evaluating Ad- versarial Robustness of Large Vision-Language Models.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities On Evaluating Ad- versarial Robustness of Large Vision-Language Models

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.709325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2c76d47f-024e-451e-a568-db48a2677b97 · outbound

This paper cites Secrets of RLHF in Large Language Models Part I: PPO.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Secrets of RLHF in Large Language Models Part I: PPO

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.382133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e19ae674-5361-406b-b663-9a91ebdf934b · outbound

This paper cites Yes” or “No.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities Yes” or “No

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:21:35.697292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers