Paper Citation Record · LEDGER

SafeVid: Toward Safety Aligned Video Large Multimodal Models

As of 18 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 1 inbound Pith citation observation for arXiv:2505.11926.

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

pith.paper-citation-record.v1
2505.11926 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:49:49.493020Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T13:13:57.233182Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

55 of 55 outbound references displayed

verified exact1
verified fuzzy25
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b1ad4736-3e7f-4374-a09c-536b091ccff7 · outbound

This paper cites URLhttps://huggingface.co/datasets/ gretelai/gretel-safety-alignment-en-v1.

SafeVid: Toward Safety Aligned Video Large Multimodal Models URLhttps://huggingface.co/datasets/ gretelai/gretel-safety-alignment-en-v1

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.221604Z

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 1f554298-3b44-49df-b871-86107684589d · outbound

This paper cites GPT-4 Technical Report.

SafeVid: Toward Safety Aligned Video Large Multimodal Models GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.274039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4c3b572-a298-4802-bba4-74a67503792d · outbound

This paper cites Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.279644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9755fe92-a1bb-42a2-9b16-895775525571 · outbound

This paper cites Claude.https://claude.ai/chats, 2023.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Claude.https://claude.ai/chats, 2023

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.208950Z

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 49337657-b6bf-46b4-90f3-079beae8302c · outbound

This paper cites Qwen Technical Report.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Qwen Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.287871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 749056c8-5454-4745-9001-dd7237aa4e44 · outbound

This paper cites Qwen2.5-VL Technical Report.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Qwen2.5-VL Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.292153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dfb6d81-d0e4-4f58-bb83-8a5c4234aa3e · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Constitutional AI: Harmlessness from AI Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.297385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb599b88-6d53-4036-89bc-c720a7a329c1 · outbound

This paper cites Safeinfer: Context adaptive decoding time safety alignment for large language models.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Safeinfer: Context adaptive decoding time safety alignment for large language models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.196776Z

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 d07f0f92-9076-483a-841c-843fb3299a0f · outbound

This paper cites Movieclip: Visual scene recognition in movies.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Movieclip: Visual scene recognition in movies

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.184265Z

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 1c27fa4e-6254-458c-aa08-798f766380a6 · outbound

This paper cites Internlm2 technical report, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Internlm2 technical report, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.171461Z

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 1bc8e709-dbcf-4ae7-8743-9fdb5d3ec250 · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.313768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efc923aa-0142-4905-a9fa-930b2d2320b3 · outbound

This paper cites Bypassing Safety Guardrails in LLMs Using Humor.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Bypassing Safety Guardrails in LLMs Using Humor

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:49:49.801421Z

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 3eaa028f-c90a-4dee-a94c-7f725ce779e9 · outbound

This paper cites Large scale holistic video understanding.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Large scale holistic video understanding

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.152016Z

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 5dc728eb-2b3f-4b94-93cf-c0df3b668c1f · outbound

This paper cites Mmbench-video: A long-form multi-shot benchmark for holistic video understanding.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Mmbench-video: A long-form multi-shot benchmark for holistic video understanding

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.140513Z

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 bef74d9b-e54e-4377-8408-7d7f50aff464 · outbound

This paper cites Videojail: Exploiting video-modality vulnerabilities for jailbreak attacks on multimodal large language models.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Videojail: Exploiting video-modality vulnerabilities for jailbreak attacks on multimodal large language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.127468Z

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 43d4ddd0-d980-47dc-9568-d6dca537a604 · outbound

This paper cites Flames: Benchmarking value alignment of llms in chinese.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Flames: Benchmarking value alignment of llms in chinese

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.114284Z

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 e9b536b1-e2df-4a50-88c4-7b0484e426fd · outbound

This paper cites GPT-4o System Card.

SafeVid: Toward Safety Aligned Video Large Multimodal Models GPT-4o System Card

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.336287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a63f49f-1614-4236-ae60-8c3b9bd954d8 · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset.NeurIPS, 2023.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Beavertails: Towards improved safety alignment of llm via a human-preference dataset.NeurIPS, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.101310Z

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 f9cf6536-2396-4a68-94db-4790b442b590 · outbound

This paper cites Pku-saferlhf: A safety alignment preference dataset for llama family models.arXiv e-prints, pages arXiv–2406, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Pku-saferlhf: A safety alignment preference dataset for llama family models.arXiv e-prints, pages arXiv–2406, 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.088917Z

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 6fd37571-ad30-40d3-beb4-445be51ea9a3 · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.348937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bd1b770-d493-4bd2-aea7-ec3638b774ac · outbound

This paper cites Awesome-llm-robotics, 2022.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Awesome-llm-robotics, 2022

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.076356Z

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 c6503423-5272-4aa4-b6d0-0fad007be127 · outbound

This paper cites RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.

SafeVid: Toward Safety Aligned Video Large Multimodal Models RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.357305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87996247-0660-48ae-a16f-955e0e181d22 · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.361201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd5c1096-4d41-4f38-b657-6a2bec385181 · outbound

This paper cites DeepSeek-V3 Technical Report.

SafeVid: Toward Safety Aligned Video Large Multimodal Models DeepSeek-V3 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.365357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecdaefe5-8393-4bf3-bdeb-8a5dd5c773c4 · outbound

This paper cites Harnessing llms for automated video content analysis: An exploratory workflow of short videos on depression.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Harnessing llms for automated video content analysis: An exploratory workflow of short videos on depression

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.063049Z

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 a267a1d3-36b9-4788-b4fc-f06d4ccf50e3 · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models Mm-safetybench: A benchmark for safety evaluation of multimodal large language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.049668Z

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 774099fb-cbb7-4933-8ea2-de38ef1c1508 · outbound

This paper cites Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.377610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f1ef541-78d0-4e95-91a8-c1c737eec1e1 · outbound

This paper cites Jailbreakv-28k: A benchmark for assessing the robustness of multimodal large language models against jailbreak attacks.arXiv e-prints, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Jailbreakv-28k: A benchmark for assessing the robustness of multimodal large language models against jailbreak attacks.arXiv e-prints, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.035464Z

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 84f96ebd-3586-462b-a13b-4756df2cd196 · outbound

This paper cites Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.385121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ddbf46d-e6f2-4f9d-b908-97f5830096ac · outbound

This paper cites Sg-bench: Evaluating llm safety generalization across diverse tasks and prompt types.NeurIPS, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Sg-bench: Evaluating llm safety generalization across diverse tasks and prompt types.NeurIPS, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.021549Z

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 a6782bb9-ce57-437e-9b32-02360622c919 · outbound

This paper cites Chatgpt.https://chat.openai.com/chat, 2023.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Chatgpt.https://chat.openai.com/chat, 2023

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:50.000483Z

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 2cbdd0da-ed37-4065-845c-49897e409b8d · outbound

This paper cites Training language models to follow instructions with human feedback.NeurIPS, 2022.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Training language models to follow instructions with human feedback.NeurIPS, 2022

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.396866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c40284-b4bf-4048-a8b9-44aa5adc2ca1 · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models Direct preference optimization: Your language model is secretly a reward model

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.400709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c11ab2f9-4fdb-4e4d-bddd-2d24434d55a4 · outbound

This paper cites Safetywashing: Do ai safety benchmarks actually measure safety progress?NeurIPS, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Safetywashing: Do ai safety benchmarks actually measure safety progress?NeurIPS, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.972098Z

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 93e2d6c3-663b-4afb-9cf8-0f6fa4de5584 · outbound

This paper cites Large Language Model Safety: A Holistic Survey.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Large Language Model Safety: A Holistic Survey

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.408428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4dda6f1-ae08-4407-9b67-7c753f65d8fc · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

SafeVid: Toward Safety Aligned Video Large Multimodal Models A StrongREJECT for Empty Jailbreaks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.412207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e8a7ae-3d92-4030-9502-67e93709b04d · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.416402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e0bef6-deae-45b9-a20e-a419c2755135 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Gemini: A Family of Highly Capable Multimodal Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.420281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c893b13c-09e9-4cd4-aef5-2b8b5883464f · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models LLaMA: Open and Efficient Foundation Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.424246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1926a5-84e9-43b1-99be-ae980477d9a5 · outbound

This paper cites Ideator: Jailbreaking large vision-language models using themselves.arXiv preprint arXiv:2411.00827, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Ideator: Jailbreaking large vision-language models using themselves.arXiv preprint arXiv:2411.00827, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.428709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a02c5f9-9ab5-47d4-b94f-cc3fd0cee864 · outbound

This paper cites InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation.

SafeVid: Toward Safety Aligned Video Large Multimodal Models InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.432833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f56e1b-0682-4489-b391-d459133a36ea · outbound

This paper cites Internvideo2: Scaling foundation models for multimodal video understanding.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Internvideo2: Scaling foundation models for multimodal video understanding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.438126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35c34c0-d8e4-40ff-8075-557ac3875cd8 · outbound

This paper cites Fake alignment: Are llms really aligned well? InNAACL, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Fake alignment: Are llms really aligned well? InNAACL, 2024

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.952659Z

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 3ea6302c-aa86-4567-a215-32da17f40578 · outbound

This paper cites Gpt4video: A unified multimodal large language model for lnstruction-followed understanding and safety-aware generation.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Gpt4video: A unified multimodal large language model for lnstruction-followed understanding and safety-aware generation

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.940315Z

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 60d04b8e-f8ff-4970-8432-cee4a9b6cd40 · outbound

This paper cites Jailbroken: How does llm safety training fail?NeurIPS, 2023.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Jailbroken: How does llm safety training fail?NeurIPS, 2023

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.928450Z

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 fc8c26be-4ac3-4ed9-aadb-16e92869d2de · outbound

This paper cites Videoclip: Contrastive pre-training for zero- shot video-text understanding.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Videoclip: Contrastive pre-training for zero- shot video-text understanding

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.915901Z

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 9d985729-cf7a-4a2c-8b8b-249824dc2b58 · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

SafeVid: Toward Safety Aligned Video Large Multimodal Models MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.459361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6831ce43-0974-4404-bd89-b022ae622c13 · outbound

This paper cites Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.464120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac69b33e-7093-439a-a44a-7a0269c42e65 · outbound

This paper cites Llava-next: A strong zero-shot video understanding model.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Llava-next: A strong zero-shot video understanding model

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.469109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd644ca-8c10-464f-b2dd-67bc22e8e367 · outbound

This paper cites Spa-vl: A comprehensive safety preference alignment dataset for vision language model, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Spa-vl: A comprehensive safety preference alignment dataset for vision language model, 2024

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.895543Z

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 9c183fa0-ef71-4989-83ac-ef253deb6fec · outbound

This paper cites Llava-next: A strong zero-shot video understanding model, 2024.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Llava-next: A strong zero-shot video understanding model, 2024

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.883593Z

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 fb1984f9-60b1-449a-bd55-baba4736575a · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Llamafactory: Unified efficient fine-tuning of 100+ language models

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:49:49.870515Z

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 1b497a68-7bff-4ef0-8468-78430bcd844d · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

SafeVid: Toward Safety Aligned Video Large Multimodal Models Fine-Tuning Language Models from Human Preferences

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.489432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1711eeb6-f979-466d-9a7d-8d254fcc51b5 · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.493020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9288a81-0878-488e-b574-c7f39e59fd2a · outbound

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

SafeVid: Toward Safety Aligned Video Large Multimodal Models LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T20:49:49.485430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9c61bd1e-6b1d-4570-b708-f7f5e7f71cec · inbound

Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Framework cites this paper.

Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Framework SafeVid: Toward Safety Aligned Video Large Multimodal Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T13:13:57.233182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.