Paper Citation Record · LEDGER

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

As of 21 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 8 inbound Pith citation observations for arXiv:2505.11049.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.11049 v1

Coverage vector

measured 95 of 95 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:05:17.701839Z

measured 103 of 103 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:56:52.768314Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

95 of 95 outbound references displayed

verified exact1
verified fuzzy8
unresolved86
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation a67d602a-7f1a-4fe9-8115-3c338a3d1cc9 · outbound

This paper cites GPT-4 Technical Report.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.276990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 059dc69b-7f28-481b-be96-4716422589e1 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Flamingo: a visual language model for few-shot learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.282637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d84771-0ed3-4111-bb82-78d040990475 · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning A General Language Assistant as a Laboratory for Alignment

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.287377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f694b416-de5d-4862-813e-b4d8b62c550a · outbound

This paper cites Azure ai content safety.https://azure.microsoft.com/en-us/products/ai-services/ai-content-safety/, 2024.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Azure ai content safety.https://azure.microsoft.com/en-us/products/ai-services/ai-content-safety/, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.292503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ca163ae-a265-40ce-a37a-53b0cc82497a · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.297130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e76503d-7782-48e2-a935-ebb166284a53 · outbound

This paper cites R1-v: Reinforcing super generaliza- tion ability in vision-language models with less than $3.https://github.com/Deep-Agent/ R1-V, 2025.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning R1-v: Reinforcing super generaliza- tion ability in vision-language models with less than $3.https://github.com/Deep-Agent/ R1-V, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.302458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77ce474a-c83f-4189-937e-caf3cdee3be1 · outbound

This paper cites Sharegpt4v: Improving large multi-modal models with better captions.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Sharegpt4v: Improving large multi-modal models with better captions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.307692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0037bc2a-e4a9-43ed-b33e-b6f8f1e4dde8 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.312329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81adb8cd-07d9-4948-814c-3be92b933378 · outbound

This paper cites How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.316854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2616f7c-47d4-4f4c-bb1a-79948b94c085 · outbound

This paper cites Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.321765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a5519a-a09f-454e-9774-509c90d902ec · outbound

This paper cites Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.326452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dadadb3f-6a3c-461b-a374-7e97571984fb · outbound

This paper cites Llm agents for education: Advances and applications.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Llm agents for education: Advances and applications

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.331925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d66acdf4-d0a9-467e-affb-1b2b856feaa7 · outbound

This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.336118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d27dcaf7-13be-4aeb-8bef-d3cf7adfdf0e · outbound

This paper cites Gemini robotics brings ai into the physical world.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Gemini robotics brings ai into the physical world

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.341152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b38f74aa-c96f-4e64-b2cc-6841eb7b6813 · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.345848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a1a86ce-35e1-4fa1-85d6-fc3bc923d838 · outbound

This paper cites VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.350734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c0641ec-2dea-441d-9c4c-dd18a68b3c22 · outbound

This paper cites The Llama 3 Herd of Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning The Llama 3 Herd of Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.355013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f855a9-3818-4406-b848-5d5bc68792fe · outbound

This paper cites Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.359178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0936b09-a7b3-43ff-8f68-e03761ecaa46 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.363940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a484e8de-fd23-4538-8126-30b10b8a0ae8 · outbound

This paper cites an unresolved cited work.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.368245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48419eff-b2b3-43aa-8648-18699d8d518f · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.372492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24f802ab-2532-4fd0-86b6-cbc7018d865f · outbound

This paper cites Mllmguard: A multi-dimensional safety evaluation suite for multimodal large language models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Mllmguard: A multi-dimensional safety evaluation suite for multimodal large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.376605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 185820a3-ab7d-4162-810a-b1408d04f017 · outbound

This paper cites Visual programming: Compositional visual reasoning without training.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Visual programming: Compositional visual reasoning without training

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.380595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2e443a1-daaf-4ab0-8d93-8f8a9da1c3d6 · outbound

This paper cites HOD: A Benchmark Dataset for Harmful Object Detection.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning HOD: A Benchmark Dataset for Harmful Object Detection

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-15T21:05:18.618597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation df4669be-510d-4d59-854e-5a83ec5e5bd2 · outbound

This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.388935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfc5856f-1c94-4deb-bc51-c33a869c334b · outbound

This paper cites Llava- guard: Vlm-based safeguard for vision dataset curation and safety assessment.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Llava- guard: Vlm-based safeguard for vision dataset curation and safety assessment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.393351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15915a3c-74a2-4415-93ec-3e26e0e5681c · outbound

This paper cites Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.397773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402efc18-f9f3-417d-ae4f-6505bb7f7b2c · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.401978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b589666-6d6c-484c-aafb-a4d794d115f3 · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Beavertails: Towards improved safety alignment of llm via a human-preference dataset

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.406640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c3021d7-43bc-4e6a-ad11-19357bca4517 · outbound

This paper cites Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.410804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 931adb0c-5bf9-44b4-8cfd-e8cf88095c93 · outbound

This paper cites RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.415290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e2df54e-8e48-4b3a-b3ed-74c4c5352818 · outbound

This paper cites Mistral 7B.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Mistral 7B

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.419833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64abdd87-a7d5-4dda-b183-49ea6da922c3 · outbound

This paper cites Chat-univi: Unified visual representation empowers large language models with image and video understanding.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Chat-univi: Unified visual representation empowers large language models with image and video understanding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.424521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96770cc3-6118-4003-8d1a-f7ea010b7729 · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning The hateful memes challenge: Detecting hate speech in multimodal memes

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.429292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 260024b7-94e6-4cdb-af70-da7cedfb86db · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning LLaVA-OneVision: Easy Visual Task Transfer

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.433581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 908556a0-3dce-45a4-be5e-46189927dcf9 · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Blip: Bootstrapping language- image pre-training for unified vision-language understanding and generation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.438082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5da9e42-6e15-4e3a-9b62-69759fa420d3 · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.442121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbf10fd8-69ae-4d28-a2f4-068400f48398 · outbound

This paper cites Mmcode: Evaluating multi- modal code large language models with visually rich programming problems, 2024.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Mmcode: Evaluating multi- modal code large language models with visually rich programming problems, 2024

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:19.092010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 99ec4a73-7b09-4444-af12-1e58b91d8d04 · outbound

This paper cites SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.450679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5636450b-7d98-474f-b87a-c3cda333cc39 · outbound

This paper cites Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.455364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a922e96a-11a4-4514-b2bd-68eeeb4aa23f · outbound

This paper cites Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Images are achilles’ heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.460803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88af99e7-e5bb-47f9-8d82-6c07a42e7bb9 · outbound

This paper cites Mitigating the Alignment Tax of RLHF.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Mitigating the Alignment Tax of RLHF

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.465819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd904c7b-fa90-4073-ad78-93f07df5ee81 · outbound

This paper cites ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.470235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 407c0151-94ac-43a0-8876-258193b23580 · outbound

This paper cites Visual instruction tuning.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Visual instruction tuning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.474745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4f63714-f7ac-4731-be31-c4345d175f20 · outbound

This paper cites Improved baselines with visual instruction tuning.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Improved baselines with visual instruction tuning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.478810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5806708-77f4-49b1-82bc-68be2b03e35b · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Llava-next: Improved reasoning, ocr, and world knowledge, January 2024

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.482772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eedd605e-41f3-43d9-9dbe-ebb9209e4fb1 · outbound

This paper cites VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.486536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565b0618-a7b4-472c-89e5-698cae603b30 · outbound

This paper cites Guardreasoner: Towards reasoning-based llm safeguards.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Guardreasoner: Towards reasoning-based llm safeguards

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.490793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94989d6d-777b-4466-9265-49011f8afb08 · outbound

This paper cites Safety Alignment for Vision Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Safety Alignment for Vision Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.495093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b13de2ec-cefc-418e-bb67-ae37a45e9e7a · outbound

This paper cites Trojvlm: Backdoor attack against vision language models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Trojvlm: Backdoor attack against vision language models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.500116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c993b70-72f8-4b99-a2d1-0c9f408e0f74 · outbound

This paper cites Backdooring Vision-Language Models with Out-Of-Distribution Data.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Backdooring Vision-Language Models with Out-Of-Distribution Data

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.505279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 350a171a-cd5e-4519-bbec-485e8f6d169b · outbound

This paper cites Dolphins: Multimodal language model for driving.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Dolphins: Multimodal language model for driving

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.510185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22dfca19-9866-4f6c-b324-6ddc483fcc49 · outbound

This paper cites A holistic approach to undesired content detection in the real world.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning A holistic approach to undesired content detection in the real world

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:19.024167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ba2a63e5-328d-4701-b870-8efbd56f3f30 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.518724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a46a5da9-a4b7-4621-8e4c-82c1d8a4e3f9 · outbound

This paper cites UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.524243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd9910a0-561f-49e1-a6d8-b86270eb78b3 · outbound

This paper cites Learning to reason with llms.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Learning to reason with llms

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.528943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322483f4-974b-4bba-9ae5-53f5c5e55108 · outbound

This paper cites Openai o3-mini.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Openai o3-mini

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:19.001302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 495f02cd-25cd-401f-979a-ada6748a15dc · outbound

This paper cites Training language models to follow instructions with human feedback.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Training language models to follow instructions with human feedback

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.537436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea9b7f1-2c64-443b-9837-d1f6c9125e4f · outbound

This paper cites LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.541570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea1e733-27eb-4a17-9008-8ba95f417416 · outbound

This paper cites MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.546000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e7da1d-e41f-4d83-8030-8ca66851019e · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.550364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f34bf84-9f7a-477d-9f4f-64922fceec6c · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Learning transferable visual models from natural language supervision

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.554503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e006d53-2693-4f53-a20d-e45eaf1afb7c · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Direct preference optimization: Your language model is secretly a reward model

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.558639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98da4e58-7aed-4619-a01d-c242a7f062dc · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.562852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9afbc52-2f71-43f2-9bb4-f37455b21ef2 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.567008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a629905-c02e-4eea-8856-54fc26684e73 · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.571466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7460475-7a16-4ef9-8d78-913abeeb5ac3 · outbound

This paper cites Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.575913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b63eb0-ee64-44d8-88fd-c300ce913979 · outbound

This paper cites Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Introducing computer use, a new claude 3.5 sonnet, and claude 3.5 haiku

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.580157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 176ad5d5-e7b9-4213-97c8-79acf6d62d6b · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.584306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d5a7dd0-5df2-4b29-907a-c88d3c7a5022 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Gemma 2: Improving Open Language Models at a Practical Size

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.588467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e784db5b-f00e-47d0-92b5-fe31e3095eac · outbound

This paper cites Introducing deep research.https://openai.com/index/introducing-deep-research/, 2025.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Introducing deep research.https://openai.com/index/introducing-deep-research/, 2025

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:18.952334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dfcd2088-ae27-431f-971b-259511c2c9ae · outbound

This paper cites Introducing chatgpt.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Introducing chatgpt

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:18.937906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8cd67b09-f600-425b-9390-538f44797f8a · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning LLaMA: Open and Efficient Foundation Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.601408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c37457a-a755-420c-b7a8-64a193dd5e3f · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.606554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f57258b7-1e11-40f5-881c-523b8d93e231 · outbound

This paper cites SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.610727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb792141-ca0b-4196-95c1-78edaee0fe2d · outbound

This paper cites Measuring multimodal mathematical reasoning with math-vision dataset.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Measuring multimodal mathematical reasoning with math-vision dataset

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:18.924012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0410eec4-6da3-4d40-b259-8077c786f5c0 · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.619466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7570a97b-53aa-4b6b-83d0-9148f392dde3 · outbound

This paper cites InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.624914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bf8de48-2809-4101-991a-ce9ab1768fa5 · outbound

This paper cites Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Adashield: Safeguarding multimodal large language models from structure-based attack via adaptive shield prompting

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:18.909918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation af966ca0-c6bf-48e9-be01-f3095f067f15 · outbound

This paper cites FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.633724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69ed006a-72cf-4d12-8bd9-e83d56a72687 · outbound

This paper cites Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.638168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75699b0f-f82f-4117-ba8d-787d3a1ccafa · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.642856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36c59657-8a5f-47a0-93b0-37920037b8c9 · outbound

This paper cites LLaVA-CoT: Let Vision Language Models Reason Step-by-Step.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.648013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dae07785-89cf-4442-9190-6316d7c3b48b · outbound

This paper cites Qwen2.5 Technical Report.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Qwen2.5 Technical Report

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.652638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0c04a05-0cf3-4594-a805-247db0fc2cfd · outbound

This paper cites R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.658163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37de5f92-a0df-48d1-9695-13beff68f5ff · outbound

This paper cites A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.663337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 697064b2-2ed7-4c2a-8bd7-9fd8e551c40c · outbound

This paper cites Why johnny can’t prompt: how non-ai experts try (and fail) to design llm prompts.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Why johnny can’t prompt: how non-ai experts try (and fail) to design llm prompts

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.667716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d880d1-eb2f-485b-a5af-ec6172f42702 · outbound

This paper cites Bad news: Clickbait and deceptive ads on news and misinformation websites.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Bad news: Clickbait and deceptive ads on news and misinformation websites

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:05:18.877089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a263dac6-bd43-4e38-852f-cef4217c13d9 · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.675851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ce7c0d-7aab-4be3-b927-d3944b69929e · outbound

This paper cites JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.680565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c06d25b-f0e5-44d6-9b3c-896d0ff2e226 · outbound

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

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.684763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ffe61f5-78b3-4105-aaa8-a6843d8e7136 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.689104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa293d81-72aa-451b-a037-650627d50755 · outbound

This paper cites Easyr1: An efficient, scalable, multi-modality rl training framework.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Easyr1: An efficient, scalable, multi-modality rl training framework

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.693337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 251eb9f7-da9f-433d-8452-a1b098bfe3a1 · outbound

This paper cites Visual In-Context Learning for Large Vision-Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Visual In-Context Learning for Large Vision-Language Models

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.697495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 553a30e5-35a0-4aa7-bd48-09c04608b4cd · outbound

This paper cites Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:17.701839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 051c2e60-111f-4a55-af41-74eb7cd6d308 · inbound

Backdoor Cleaning without External Guidance in MLLM Fine-tuning cites this paper.

Backdoor Cleaning without External Guidance in MLLM Fine-tuning GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:52.768314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c410194b-5efe-44fa-be0b-30da1f4a9e0f · inbound

FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models cites this paper.

FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:58.778782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e07cbb-957b-427a-85e6-c69613736d1c · inbound

Agentic Web: Weaving the Next Web with AI Agents cites this paper.

Agentic Web: Weaving the Next Web with AI Agents GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 142

Resolution: unresolved; no resolver link, observed 2026-08-06T13:05:39.587941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60da59e6-f61a-459e-bab8-d9b9168187f0 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 133

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:06.976193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6b8d6d-4372-4639-b0c1-1623d1bf4361 · inbound

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models cites this paper.

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T20:14:04.067928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c30ea03c-5e62-460b-93eb-e59047fb9000 · inbound

RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation cites this paper.

RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:15:54.719220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b0705dee-1da8-4612-8130-928437d6063e · inbound

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:19:26.804410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 486c9195-9b14-4023-bb9b-b966f0c70219 · inbound

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections cites this paper.

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T14:45:49.566560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.