Pith. sign in

Paper Citation Record · LEDGER

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs

As of 22 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 0 inbound Pith citation observations for arXiv:2607.27917.

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

pith.paper-citation-record.v1
2607.27917 v1

Coverage vector

measured 62 of 62 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T23:07:40.703981Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

62 of 62 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved62
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fd3f871f-9b00-4819-8da2-137ffd571274 · outbound

This paper cites European conference on computer vision , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs European conference on computer vision , pages=

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:35.935760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:35.935760Z digest=sha256:01e6f2d63536dc62a032ef89e84cc5204f532b178f64de5171e7390b6fcf207d

Observation 133a6bc0-f043-4acb-ba93-55dc38974415 · outbound

This paper cites Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:35.993298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:35.993298Z digest=sha256:ffb72bb8752e60b33e53d71308b54e5068162d3393ca07d51dd470c35794f6a3

Observation 1f7f651c-e219-45da-b2f0-6f338ce1acd2 · outbound

This paper cites Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

Reference 3

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.082026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.082026Z digest=sha256:1533f444b0e477f94b619cb014cc42a75c50bcf1a5a435573dd10bc47e33943d

Observation 75e3594a-b3af-4374-bdc9-f07a959b59bf · outbound

This paper cites Language Models are Multilingual Chain-of-Thought Reasoners.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Language Models are Multilingual Chain-of-Thought Reasoners

Reference 4

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.204013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.204013Z digest=sha256:5010e181a165022d507fc9bdcd26366b24ae14b349e1f61797a35cdcd06d7368

Observation a992a3aa-7725-4158-8c0f-e633cf16e867 · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.307426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.307426Z digest=sha256:9cbadfba7f8cb96f539c445cb8690b8272c0826c2a34637d475e5f52bde068fa

Observation 56abfa45-263a-4f17-954b-760b114f8451 · outbound

This paper cites an unresolved cited work.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.430639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.430639Z digest=sha256:014fa1dd87110531ae67bcecfddda359060528c52fda8885561cb7e219b8f6e9

Observation 7a1f4b58-35ab-4406-b8f6-42bab4e1ad12 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 7

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.552810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.552810Z digest=sha256:22fa6cc767f289513e2bd3079e3b74ea99bf4b0f6e7a927a35dc4b66ae6a77ec

Observation 5e49c6d3-bd7e-415f-b692-04789352c566 · outbound

This paper cites Proceedings of the 31st International Conference on Computational Linguistics , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the 31st International Conference on Computational Linguistics , pages=

Reference 8

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.655085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.655085Z digest=sha256:58b5d9a8e75e3551b8e185b839a1f0762387ae1da83223b20ad266cc13f00026

Observation 681b59c6-4639-43b0-a0e9-ac25a2d2e2a4 · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 9

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.745408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.745408Z digest=sha256:19ca02b86830d980abca2dbc03175f56323650ea5e754899c36995be02ade3d8

Observation ffeae474-a4cd-4c55-92f5-af38420bc189 · outbound

This paper cites International Conference on Learning Representations , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs International Conference on Learning Representations , volume=

Reference 10

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:36.853108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:36.853108Z digest=sha256:18c66c54bd4b2aae688f95a1992966a5771e7f8a8e5b401bfe8215480f96d0d9

Observation 1016aaa0-f795-43ff-b6a8-89555317008c · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 11

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.017335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.017335Z digest=sha256:8998513d883ae1ff29f77bd07f75199f28281e7efb63b4157eace035be8c127b

Observation 5d8e7b1a-38f8-4e90-90e5-58135c4c9bf3 · outbound

This paper cites International Conference on Learning Representations , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs International Conference on Learning Representations , volume=

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.182036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.182036Z digest=sha256:a19126d5e2667e795ac7e6c456faf849d5713056dab555a5cdc329c395052b33

Observation a16dbd1a-abc7-4b4d-b498-c1dd770bbc08 · outbound

This paper cites European Conference on Computer Vision , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs European Conference on Computer Vision , pages=

Reference 13

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.191517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.191517Z digest=sha256:7c93f96947321e27b69423f7cdc7310a9fa254f33e3fdd469a2ead2152d2e0d4

Observation 7126683a-5269-449d-a4d7-933d1fc47bcf · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.279483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.279483Z digest=sha256:4350fc02d7243ab2df081498a406d801738e5a20fa840a0e97c0ea539e05687c

Observation 8b4147de-8502-4cb8-81fd-7eac66ec63ab · outbound

This paper cites Advances in neural information processing systems , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Advances in neural information processing systems , volume=

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.391270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.391270Z digest=sha256:3e67e97c55e4b0e4ca034259369f72bd03fe67f11f319685b5863e9132fcc6d9

Observation 45baa0b1-3fc8-47c1-9162-08883b253236 · outbound

This paper cites ACM Transactions on Software Engineering and Methodology , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs ACM Transactions on Software Engineering and Methodology , volume=

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.474234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.474234Z digest=sha256:379aa83a0b7c080a25a3df39f3c4775c8e99deaa5c327aaab74c823605b72b44

Observation 6c261576-7405-40f9-bbb1-2588d573b740 · outbound

This paper cites Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.594638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.594638Z digest=sha256:f79ba26cb240cd76cb04b0b1315c38eecab417e36933066aa907026ae2113a8b

Observation b1f9f076-952b-49f0-bf20-7b97512151ec · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 18

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.687091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.687091Z digest=sha256:978381560557ddadb39f72841e85f162a59adf8eff8db4f0243e70de3be1f989

Observation 8de8a063-9dcf-4e76-9e64-8c84e35b6e2a · outbound

This paper cites , author=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs , author=

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.792813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.792813Z digest=sha256:9f772021484d8679891420d42ef9b08d10241a47a2f4e45786251676c4840f97

Observation bd21d3ed-76c9-4ed8-a11e-02eec9a335a4 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Finetuned Language Models Are Zero-Shot Learners

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:37.939490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:37.939490Z digest=sha256:fd63b9ab7c57f2fb78b6147c91f2ca55fe7cdab4af343ef44a22ee5ca1f17822

Observation 9d059432-56aa-49aa-bbd1-bd046862da47 · outbound

This paper cites Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers) , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers) , pages=

Reference 21

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.066884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.066884Z digest=sha256:e870d48c7af9877209fe16ac06ac58c48c74981c35fda9f68e07e0f7c7a83598

Observation 4ca2c401-ee6d-428b-a167-48ab331957aa · outbound

This paper cites ACM Computing Surveys , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs ACM Computing Surveys , volume=

Reference 22

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.144990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.144990Z digest=sha256:a24f969ea654c98096b4268c3d9fc3ad61c5930e5b4051f9e5cf464b03025411

Observation 30b18abd-8760-4705-9392-f6355cb65a52 · outbound

This paper cites The Second Tiny Papers Track at ICLR 2024 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs The Second Tiny Papers Track at ICLR 2024 , year=

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.201864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.201864Z digest=sha256:c907d82f54976a7e8f908396b3680a24e5e22df83a8f3bff23823d91fc118f11

Observation 81806b67-2981-4e5c-8ba6-cb19f5e76ddc · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 24

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.361982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.361982Z digest=sha256:e78f724d4a13eee676e02c94f88e49444d8e788113441cdcd5adaae5fab77acf

Observation ed631c78-ac9d-43aa-a90d-4307cc4386a4 · outbound

This paper cites arXiv preprint arXiv:2602.16660 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2602.16660 , year=

Reference 25

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.471659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.471659Z digest=sha256:d11f8691ae32d061846a8e12846b006a0e7551a34e14ea4085955cca410dc4e4

Observation 584c995f-e288-4597-85ff-85fd2641b81f · outbound

This paper cites Qwen3 Technical Report.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Qwen3 Technical Report

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.605144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.605144Z digest=sha256:2b9842a76952eeec968063f8437bd0eb51fdba52dd48363292ea16bdda7f0e86

Observation d7bc1f4a-9ff1-4d9e-8b03-bdb6ff4c91ae · outbound

This paper cites The Llama 3 Herd of Models.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs The Llama 3 Herd of Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.757243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.757243Z digest=sha256:6b1108f7014c0fe793a68fd9c5f0177977d4786a0dccc229a10bf8d06a9cd783

Observation e2e490ba-21df-4a62-a7d0-872b3bd31cd8 · outbound

This paper cites Qwen3Guard Technical Report.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Qwen3Guard Technical Report

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:38.966539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:38.966539Z digest=sha256:1d42485e21f3a8febac2e3f7a75a99622b460a51b7cee2a55a6808de04c55610

Observation 3de16b2c-19d9-4625-b2ee-bea6dddf1b1d · outbound

This paper cites Gemma 3 , url=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Gemma 3 , url=

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:39.158685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:39.158685Z digest=sha256:857244b4f82be1b4461bc3837eaea193c86433b0f47b94016bf2a51832110091

Observation fe5ca6f9-705d-4a06-8675-7d75f0c7c56a · outbound

This paper cites The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts

Reference 30

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:39.332550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:39.332550Z digest=sha256:d2346c479fcd52cd7e4dfab8c8613f645730ba8a5ae8c8b37384c1c5d08ff8e7

Observation dcf6dd98-11dc-46df-b27e-de89b9960471 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 31

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:39.500723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:39.500723Z digest=sha256:705003bf6ef7292958539db78367d6e11ce5bdd15ac447c573f0048c4898bab6

Observation 53f02781-5f40-4ffe-83be-24dd3ce21925 · outbound

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

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:39.645899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:39.645899Z digest=sha256:0e85318d766839dcee2ca55aaca71df91cf46e91361d3ced7f9d6b3f9414710c

Observation a536787a-3a5f-4751-9dba-ec9f93c6c34d · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 33

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:39.746628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:39.746628Z digest=sha256:6093b50ce9e76880834816ce0f90b610c5ae71aa064d0a18e0c8582542f24256

Observation 41779b05-969d-4d32-8215-6b4c5ec77c4b · outbound

This paper cites European Conference on Computer Vision , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs European Conference on Computer Vision , pages=

Reference 34

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:39.825200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:39.825200Z digest=sha256:b5f385929af60dbd5b0cebaabdb1ce5725ea2bfc2a06374d0f9b0344f1e9aab6

Observation 07a487c6-9b7a-4608-b51e-29d8e149ba68 · outbound

This paper cites Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 35

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:39.941483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:39.941483Z digest=sha256:c773b10bf000248016f9cc93e4f89d80e6251bf6da4652e51df85de9d5e6faae

Observation 27035e5d-4456-46c9-8155-230aefb14533 · outbound

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

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time

Reference 36

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.056533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.056533Z digest=sha256:884467146f05297a730a9d45e2b9ff1ce88f36ecfcb89536b0748d40fe4634f5

Observation 784a0260-e9d2-4bb0-9d49-1ee3e05ce610 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 37

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.173637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.173637Z digest=sha256:17cccefad05cf676993f9eafa0cc55ebedd8ed0452c30018dc5ea5cbc36f940d

Observation 75d22052-f3c0-4641-96d7-43c4295008c0 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 38

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.263461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.263461Z digest=sha256:96671cc445414127b86a86540d69036322c965dbb58fca738e7502c271bc1115

Observation 5fe0b2d2-2cd5-44f2-be61-3ae44e37aceb · outbound

This paper cites arXiv preprint arXiv:2508.01710 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2508.01710 , year=

Reference 39

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.331051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.331051Z digest=sha256:97c3d893ff03f1ba6e71f790b086573a8cfa0c93d125a7ebdc648d0890aa3319

Observation f0361a0a-a3ba-47dc-a2d9-4bdd3ed26e80 · outbound

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

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.461286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.461286Z digest=sha256:ee9eb680b5647786c6f53f3075e8b1f59514fab09ea9295ae0ddd2c1f5e00c55

Observation 94f18b36-34e8-40e2-9d12-de108b0c5073 · outbound

This paper cites IEEE Transactions on Audio, Speech and Language Processing , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs IEEE Transactions on Audio, Speech and Language Processing , year=

Reference 41

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.579136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.579136Z digest=sha256:fff24a62f2fed5c4d9bcc01c6887e303a1fddbc86d6455c4d035c18f538ee080

Observation 9b14b217-0af7-4e06-94ec-d57e4102de52 · outbound

This paper cites The Emergence of Abstract Thought in Large Language Models Beyond Any Language.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs The Emergence of Abstract Thought in Large Language Models Beyond Any Language

Reference 42

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.584497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.584497Z digest=sha256:4496c15109e453992eff9ea3b903e0e7c0527910df4599a62a4ba1dcdb8c014d

Observation 624b69ff-e909-451c-8e86-49129598f8a2 · outbound

This paper cites Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.591567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.591567Z digest=sha256:c982d1c958ce40a4cc18f16fb113d647988695f445147cdfba8f9f606e4a43fd

Observation 03255389-28a1-4914-b697-4d22730f8899 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 44

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.597357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.597357Z digest=sha256:d9829c07f10b60c32a7b1e9d47a1bf81fafb63bc384e32aa3642d52ecffdb76b

Observation a4627470-a864-4959-869f-cad90f043c2e · outbound

This paper cites arXiv preprint arXiv:2512.01797 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2512.01797 , year=

Reference 45

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.602585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.602585Z digest=sha256:71a6a9c49645b6757fb9819aaaf1155fc33c0f239299a97e2fdcaf6f80e99588

Observation 8e4f3834-4db4-4116-83d0-a509d9f04783 · outbound

This paper cites arXiv preprint arXiv:2601.22515 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2601.22515 , year=

Reference 46

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.608491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.608491Z digest=sha256:0410013a8d7bae61a66c872febf13fe778618df7c4a4f08026aac36f51a6ebce

Observation 10d4bf11-73d2-4c14-8106-1fdd9dd846f2 · outbound

This paper cites arXiv preprint arXiv:2602.12158 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2602.12158 , year=

Reference 47

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.613089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.613089Z digest=sha256:d6fd28a35a880d1db6fa84c5502bb87c4131b74c42615da8d94c300c6adda815

Observation 9c0f034a-74f1-41ae-9af5-115923c77da6 · outbound

This paper cites arXiv preprint arXiv:2508.09190 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2508.09190 , year=

Reference 48

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.619071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.619071Z digest=sha256:913e858542c128e812d457f6192510dc26ebab86e46f47fa0f804f37ecb70789

Observation 60c0a32a-3f1b-46d5-b624-01371894f87b · outbound

This paper cites arXiv preprint arXiv:2602.01283 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2602.01283 , year=

Reference 49

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.623711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.623711Z digest=sha256:960961b2ddd486e51fe79642aa352ede585aca3419fa37e9a6acd66a4ca470ff

Observation 49802612-a72c-4b0c-8d81-951c9ed814d5 · outbound

This paper cites ACM Computing Surveys , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs ACM Computing Surveys , volume=

Reference 50

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.628291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.628291Z digest=sha256:1b8f789dc2cbea9742d607265c0ddbce7e9e3927e0dfd688d4d0d0e30938405b

Observation d8a0564f-c64e-408b-88e2-7bac95c2c47a · outbound

This paper cites Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V

Reference 51

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.633732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.633732Z digest=sha256:1713c8a1946617fc37994d1836bfbdecd46b49b8510b291d7a7cb19075f33a64

Observation d29e533c-f2a4-4e6f-b021-fc32278d55d6 · outbound

This paper cites BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning

Reference 52

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.640029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.640029Z digest=sha256:dc9aff7cd196aa230616f542136d74a8aa4013dd02dfec632d3ba109a00e776c

Observation 946d968e-68ff-4949-b67c-01c0074a1da4 · outbound

This paper cites Learning, Media and Technology , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Learning, Media and Technology , volume=

Reference 53

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.646292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.646292Z digest=sha256:5fda5b9edfeed422af26ebf24c9d3981a4e8900e6756f8d3db2cf04d5022c41a

Observation cd001eb1-32a0-4b4e-8862-f544de839176 · outbound

This paper cites Advancing LLM Safe Alignment with Safety Representation Ranking.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 54

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.652133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.652133Z digest=sha256:61ececf669ac1d2fe475941cd0ea9b459d9d813e643e2c9758dcd034ae2b8e10

Observation accc4ea6-233b-4648-9073-415658571699 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 55

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.658375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.658375Z digest=sha256:bc944aea82f0b6b1b1755f78657fd49a6bb389b2cf171bcedad7a83b58c40f1c

Observation 30b5dc05-c6e8-4b61-88ba-a2e4b0efa523 · outbound

This paper cites arXiv preprint arXiv:2601.14298 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2601.14298 , year=

Reference 56

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.663190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.663190Z digest=sha256:8b19c3262364fc9b34e8fdff87dfe5be8978b8c628ca55dfc1789243156ef40d

Observation 42473ed6-fe97-4561-a313-a846dc1b3ba9 · outbound

This paper cites arXiv preprint arXiv:2602.22554 , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs arXiv preprint arXiv:2602.22554 , year=

Reference 57

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.669970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.669970Z digest=sha256:37b043273682a89ed11fca6a9d53d60badbee4d665f614b96f29cf4cc00105b4

Observation f1b08745-b835-4965-9b21-0ee383f25942 · outbound

This paper cites Journal of Machine Learning Research , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Journal of Machine Learning Research , volume=

Reference 58

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.679856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.679856Z digest=sha256:d21fdf74a7c93852cc4e2360f426a82f80060070958cde64feb227749169a7ce

Observation bcfd39c0-cf36-4cde-8840-92ba590592f8 · outbound

This paper cites Open Problems in Mechanistic Interpretability.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Open Problems in Mechanistic Interpretability

Reference 59

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.684953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.684953Z digest=sha256:ff62925fd6dfb544501a94a6d66aa74995e8bfeee9cbb79ab2b2f7b19a01dd1f

Observation 029475cc-f035-477b-bde1-e23eddc39a4b · outbound

This paper cites ACM Computing Surveys , volume=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs ACM Computing Surveys , volume=

Reference 60

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.692871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.692871Z digest=sha256:d2f69058b392418cd7f3ea15a5c1aa72a3b7e580cc985e1d038e6e10a86bbf89

Observation 7d0c1e44-7281-4275-b932-413c6f973616 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 61

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.698924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.698924Z digest=sha256:a007dd3917ad33ac3cf7431e5960be03b9dc1d473ec69c379f06a38ce0da0ca2

Observation 811c3b81-5d9e-4211-99e0-7e3cfa079ec4 · outbound

This paper cites Forty-third International Conference on Machine Learning , year=.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Forty-third International Conference on Machine Learning , year=

Reference 62

Resolution
unresolved
no resolver link, observed 2026-07-31T23:07:40.703981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T23:07:40.703981Z digest=sha256:d11706cce7641844a8397f50314208395e60911ccfd83ba3f26e1caffe926115

Pith citing papers

No inbound Pith citation observations are available.