Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models | Paper Citation Record

Observation 5a6c1927-51ab-4667-b0ca-dec37a605438 · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Emu3: Next-Token Prediction is All You Need

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.844681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dd4b622-4023-46f6-bf39-96e13017a4f6 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.850906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 705331df-483f-455e-8de1-efb72dc79792 · outbound

This paper cites Vision-language models for vision tasks: A survey,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Vision-language models for vision tasks: A survey,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.856451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df1aeae7-2ad4-4d4e-bda9-fc364eef68cc · outbound

This paper cites GPT-4 Technical Report.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models GPT-4 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.863135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 732c6b87-0776-4659-8727-9d9ce696ee0d · outbound

This paper cites Ruart: A novel text-centered solution for text-based visual question answering,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Ruart: A novel text-centered solution for text-based visual question answering,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.211359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7a0c4457-cf1a-40ab-ba9b-0aabe9c8bf3d · outbound

This paper cites Linin: Logic integrated neural inference network for explanatory visual question answering,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Linin: Logic integrated neural inference network for explanatory visual question answering,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.196836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f3eaeb8b-6572-459b-805d-d3e4ac394137 · outbound

This paper cites Expllm: Towards chain of thought for facial expression recognition,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Expllm: Towards chain of thought for facial expression recognition,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.181461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fa31761e-3949-45f7-ae22-ae12307ef775 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.883404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19fd6cb6-5199-42b1-a544-74eef5f45091 · outbound

This paper cites Knowledge enhanced vision and language model for multi-modal fake news detec- tion,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Knowledge enhanced vision and language model for multi-modal fake news detec- tion,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.165122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d7883bfb-5416-46af-9320-1330ee05f87d · outbound

This paper cites Llavanext: Improved reasoning, ocr, and world knowledge,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Llavanext: Improved reasoning, ocr, and world knowledge,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.891839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91690a51-a790-4cb0-b52e-7b3c72d0f213 · outbound

This paper cites Qwen-vl: A versatile vision-language model for understanding, localization,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Qwen-vl: A versatile vision-language model for understanding, localization,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.135648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1b6aed19-8c64-4c38-8411-0b45853f4038 · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.901249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8636a464-0b69-4b26-b346-0146e9b89072 · outbound

This paper cites Single-stream multi-level alignment for vision-language pretraining,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Single-stream multi-level alignment for vision-language pretraining,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.116712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation af2a794a-b995-438a-a53a-b4fab9baa6f2 · outbound

This paper cites Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.091241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4f91fc69-fbbc-49fd-b064-376ce816d7de · outbound

This paper cites Vision-language pretrain- ing: Current trends and the future,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Vision-language pretrain- ing: Current trends and the future,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.071233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 186cde67-7b07-4077-919c-ee7175e5e096 · outbound

This paper cites A Survey of Vision-Language Pre-Trained Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models A Survey of Vision-Language Pre-Trained Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.920538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc414044-ae4e-479d-9620-7aa3391eab6c · outbound

This paper cites Transformers in vision: A survey,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Transformers in vision: A survey,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.925962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be71c3e6-5392-4787-aecd-32ba8100a00f · outbound

This paper cites Cross- lingual adaptation for vision-language model via multimodal semantic distillation,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Cross- lingual adaptation for vision-language model via multimodal semantic distillation,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.042240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b1b6e5af-3d42-4610-a470-8477641d84bb · outbound

This paper cites Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:56.017957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a80673a5-59e8-4f1b-80fb-c3c90d84af93 · outbound

This paper cites Can llms’ tuning methods work in medical multimodal domain?.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Can llms’ tuning methods work in medical multimodal domain?

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.998949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 53901ce1-f86b-4d32-9791-64d749a30aef · outbound

This paper cites Are aligned neural networks adversarially aligned?.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Are aligned neural networks adversarially aligned?

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.976007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f7dc6641-c263-4060-84e6-747a630c28fa · outbound

This paper cites On Copyright Risks of Text-to-Image Diffusion Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models On Copyright Risks of Text-to-Image Diffusion Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.948412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d58ed6e-7da7-40da-8584-d3fb9e3af728 · outbound

This paper cites Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:25:55.572720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7e635d3c-7930-45cd-a37b-b5358f81ed5b · outbound

This paper cites Expanding Scope: Adapting English Adversarial Attacks to Chinese.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Expanding Scope: Adapting English Adversarial Attacks to Chinese

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:25:55.547598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 82d50c74-e9a1-4e10-84a4-005db90a5202 · outbound

This paper cites Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:25:55.524211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c640f369-dca2-470e-8be3-0374fbec7979 · outbound

This paper cites Adversarial attacks on deep-learning models in natural language processing: A survey,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Adversarial attacks on deep-learning models in natural language processing: A survey,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:54.971698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7320f61b-dcd2-4c9c-babf-55d5cc4b1c8c · outbound

This paper cites Many-shot jailbreaking,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Many-shot jailbreaking,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.948101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 41958f57-8d55-4563-899c-645a5bff8932 · outbound

This paper cites Initial response selection for prompt jailbreaking using model steering,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Initial response selection for prompt jailbreaking using model steering,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.932049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3758d75c-3d22-417f-9c75-4ed65546a083 · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Beavertails: Towards improved safety alignment of llm via a human-preference dataset,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.914971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 204ed18b-7f22-424f-8299-047e8f6a7c45 · outbound

This paper cites Recent advances in online hate speech moderation: Multimodality and the role of large models,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Recent advances in online hate speech moderation: Multimodality and the role of large models,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.888833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b8b60f64-dcbb-491e-81ac-adf098b03351 · outbound

This paper cites SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:25:55.496056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ef930ae3-308a-4479-ae13-6f773fe41427 · outbound

This paper cites Visual instruction tuning,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Visual instruction tuning,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.013375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85ef221a-2284-4b52-afe7-5acdb8aeec56 · outbound

This paper cites Improved baselines with visual instruction tuning,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Improved baselines with visual instruction tuning,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.019936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be409a53-35c4-4ce7-9730-8bd847b04c7a · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.025146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c5ce87-f4d7-4fd6-ba0a-a17814a1e47c · outbound

This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.036577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b62fd4d-4d61-4d67-ac3e-35de3395c7f4 · outbound

This paper cites Automatically auditing large language models via discrete optimization,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Automatically auditing large language models via discrete optimization,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.839054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21bc42eb-3179-4d34-b1a2-5d6df52742d0 · outbound

This paper cites Sensitivity of adversarial perturbation in fast gradient sign method,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Sensitivity of adversarial perturbation in fast gradient sign method,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.820693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6565244e-3082-400d-8c66-a9983a9a5b07 · outbound

This paper cites Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.054008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42587ae5-54d0-43ec-827f-d5f42df8fa1d · outbound

This paper cites Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.059952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e935f0d9-eb2b-400a-96d5-da4ed0bfeee9 · outbound

This paper cites Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.064809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 916ad6f6-f012-41d2-8414-a9fbb17f21ee · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.069605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12c20f4d-b595-436c-a237-9586189e6994 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.075571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30f57e83-21f8-4faa-998b-68177e063140 · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.084303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d65a151-61fa-4fea-bf6d-bd0608ce2dbd · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.089780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23bb944b-9264-4f3b-a8fb-8369d3702ef7 · outbound

This paper cites A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.095257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2e2b86-141e-493b-a58e-0e75f00be4e4 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.100347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1005bcbf-d5d3-4f4b-aa65-4bb452d31ace · outbound

This paper cites Adversarial Demonstration Attacks on Large Language Models.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Adversarial Demonstration Attacks on Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.105777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95f20048-6976-4cde-bcf2-2af1c69c0214 · outbound

This paper cites The hateful memes challenge: Detecting hate speech in multimodal memes,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models The hateful memes challenge: Detecting hate speech in multimodal memes,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.803319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4f818ba9-efa0-41f6-a64f-7df6b755f483 · outbound

This paper cites Words or Vision: Do Vision-Language Models Have Blind Faith in Text?.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Words or Vision: Do Vision-Language Models Have Blind Faith in Text?

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.114952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3082215d-6c67-40cf-9f02-11bea55c8486 · outbound

This paper cites Attention is all you need,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Attention is all you need,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.121467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9d8afc5-bf34-40b6-8d5b-86660bb79f8f · outbound

This paper cites Layer Normalization.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Layer Normalization

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.126609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af35e8b4-42d9-4e80-be8b-aa6374db1b08 · outbound

This paper cites ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.131501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 377bc4c5-136a-4e59-a5a0-545925f4f1c5 · outbound

This paper cites How Susceptible are LLMs to Influence in Prompts?.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models How Susceptible are LLMs to Influence in Prompts?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.136843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 166ab120-6489-4650-9969-ea61dc7597cd · outbound

This paper cites Jailbroken: How does llm safety training fail?.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Jailbroken: How does llm safety training fail?

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.771711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cf7506da-f3c4-48d6-a15b-a5a6cff5a767 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models Refusal in Language Models Is Mediated by a Single Direction

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T16:25:55.149269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e1b1f2-e691-4c03-bb59-cd18192effab · outbound

This paper cites The llama 3 family of models,.

Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models The llama 3 family of models,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:25:55.757084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers