Pith. sign in

Paper Citation Record · LEDGER

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models

As of 8 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2507.21637.

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

pith.paper-citation-record.v1
2507.21637 v1

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:40:05.603091Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

52 of 52 outbound references displayed

  • verified exact0
  • verified fuzzy2
  • unresolved49
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4a0c7dc7-677c-4d45-a9c9-fb42d716b577 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.200502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.200502Z digest=sha256:d2f95671dba6251134bfb689714f0f09ab74ceecb4a70d907a20045790b06279

Observation 938a2716-745f-4b1a-b0f4-3d8142792ad8 · outbound

This paper cites Qwen2.5-VL Technical Report.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Qwen2.5-VL Technical Report

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.218152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.218152Z digest=sha256:9d2ce538b79c7d50e39e5aa1005b8605e2210fdad4bd59e375244823804a11d3

Observation 803356ae-3ef4-408b-b5b6-d0fbab2119f8 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:07.140093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.226516Z digest=sha256:2e7f393c4d12cfc23e34cb7dc942268a5853996a779dc18f631edce0b0786a65

Observation 526e14be-75b3-451e-8b68-4263e38ed3eb · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:07.120767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.233747Z digest=sha256:a715f6c1fbfb397a47128b91fc1cff1ba49fd53f0b4abc80cc0c8a96e59d6213

Observation 7c73763f-957a-4d54-85d8-a689f283055f · outbound

This paper cites Salman Asif, Yue Dong, Amit K.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Salman Asif, Yue Dong, Amit K

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.240221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.240221Z digest=sha256:e5cc636acfe5e76198d275cd96cb6bf7eb68ca06678f1df791aaeed8e0eb4d13

Observation c0c4f28f-30e9-41d5-bc5b-ff469419415a · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.250931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.250931Z digest=sha256:4b3b55720e056dd36072a3e16a50c723a973998c1f79c499ee45015ad8299a54

Observation d4b35756-10ae-46aa-82b6-46ff3afcef04 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:07.103778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.256828Z digest=sha256:f7290d9c425918377116bc06aafdc3194c4bb12368a6d228f682115dffe1e381

Observation d88fe0ae-ef30-4399-9520-55928cf4a33f · outbound

This paper cites Glass, and Pengcheng He.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Glass, and Pengcheng He

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T12:40:07.085064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.267850Z digest=sha256:50147029ca396cd75c325c3bb4b20cac5ee284f8716bc0c6412daf002f455c0a

Observation 7c89d25c-3640-465d-bbf9-8259c92528ba · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:07.058341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.273585Z digest=sha256:cc0731f7ddb9f7e98896b92be073cfe68a92bc904d7e2c1785b3541d5c8d37a6

Observation 74f63d58-2ab6-4783-8d57-c8b8257f9d22 · outbound

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

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.281011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.281011Z digest=sha256:d18d74530e787d777a40b9aecb22ec035eef04b6a80d06f798f514ba6aad1a6a

Observation 4f27bd73-024c-4e13-adfe-8123bb08ea74 · outbound

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

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.291273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.291273Z digest=sha256:4c30aed985112bacca696bfc6d8e6834b1500adf2f057ae4dc72c9cf9699a840

Observation 86af052c-fb95-4997-8429-6b7d3904fb44 · outbound

This paper cites Kwok, and Yu Zhang.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Kwok, and Yu Zhang

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.308750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.308750Z digest=sha256:4d4f13c0534513764b101bed47d9a24bfa656c567f8b209ccbc9fed376646ae7

Observation e16a3006-54bc-4432-96cc-df5bf4579552 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.318618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.318618Z digest=sha256:c9ce1028679ed1bd70759ee890abf4424df19b73b6b8a2aab4e75b4db108218c

Observation 3815615d-fdc9-4733-8737-0c8df6ac1377 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:07.020725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.328492Z digest=sha256:395351e010658eff7cac29c45c5c966f3559dc736744582c2d2b5c9c8d3cb1c6

Observation 9874144d-d649-43c9-bfbf-92aec1c819d2 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.335370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.335370Z digest=sha256:dbff8167b11588c57729cb93fe0f5311259a10e4fc10c0ed483be65644bb1369

Observation 5fc42ab4-9d73-4090-8170-d4529d5ba78d · outbound

This paper cites Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.341720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.341720Z digest=sha256:bc66ff0cf4a69d3902e46c94f96481d3b084fb39e9508c3e98b7cb895bae7be1

Observation b40221bc-1774-4a03-a8b7-f0af564c0ee7 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.989591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.360672Z digest=sha256:7697f6a61ea978cdf7fcd4bc298e0577f41299f55dd1e1e9f3ca9c3d2817aa77

Observation 2fe66758-2e08-4023-9304-f9d39f6255da · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.367309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.367309Z digest=sha256:1bc6804b04d661693bcb91cb67401423ea1648f2183220cb2afe0d1047191ffc

Observation 146d9c65-fcc8-43b8-b978-2a0ee4f497db · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.376963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.376963Z digest=sha256:ce83a1a1fa0ba60dfd158bab369fe8824195752dfe7e4653e5f71be6a0d78a21

Observation 575f0771-f462-46bb-b03e-c85aa6957b2e · outbound

This paper cites Visual Instruction Tuning.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Visual Instruction Tuning

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.383376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.383376Z digest=sha256:1f6637930bba63b30a1ca057d1a82f5488b1d9e248354aea99d19be56c159f87

Observation 71e91868-e412-4143-9209-bc4ce3002378 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.935823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.390171Z digest=sha256:b2680239a57e2b01b14238a217b9d21fa2f04884e4ea14188f7f44116531da1e

Observation 0326b151-7096-46de-a7f0-895506175556 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.397340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.397340Z digest=sha256:7312c5d11f91afcb6299cf41172fcf85c7a8a9791b2022227000fc28450391b7

Observation 816a0154-03de-4c6e-9bd8-0b9b3ca1bdc4 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.404635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.404635Z digest=sha256:7488afc1aebfab488b267e90944e0a20a542995202941500b0fb388e02f137d3

Observation 27cfc3f2-aa59-4c32-9679-82333b3d1c35 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.411811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.411811Z digest=sha256:78b6f7b3e514f04d383f87f56a5a5feab6e05a968827a184a29a807381f7c1cc

Observation 4c76b68e-ddb7-4c99-8ef0-83cc44840e74 · outbound

This paper cites Jailbreaking Attack against Multimodal Large Language Model.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Jailbreaking Attack against Multimodal Large Language Model

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.428251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.428251Z digest=sha256:7626d86a5102aa63cf491b71da305ccdfeca7646d46fcfb198e834327c432781

Observation e3700104-9b19-4052-8196-7c2dbfffa875 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.438099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.438099Z digest=sha256:a65f5e312b513de8cb1ef6ddd581ee63bf7856f84bd3d8b85eaf8202cc023629

Observation ec82d53b-dd14-45c5-94e2-0d1aadb7788f · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.875124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.452943Z digest=sha256:2b764694a5bf535c0cab7f5003a7e832d6773ca8a3aba5260136c73e16d086f1

Observation 16dbfaca-c2c4-424d-8a20-4a383181cbb5 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.851069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.461523Z digest=sha256:33b827000aadf242f44a475583c9a3a195c474fd1b2f091f039077f00140ad0d

Observation f48ae587-50f3-421a-928a-4dc812861317 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 31

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.830398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.470324Z digest=sha256:e485bcc370e86f9c7f555c37fe6b98581562c73ed71eeff8a2c917e2e49611d1

Observation 8fdee924-2895-4cb7-85ea-706ee368dccf · outbound

This paper cites Qwen2.5 Technical Report.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Qwen2.5 Technical Report

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.478036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.478036Z digest=sha256:bddaa4888b08a963894cdd2440dfaaf49e22278f26ec9f1af245b55e19207b26

Observation 7f4a6df9-93f5-4c46-9779-9b078ef59303 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.487898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.487898Z digest=sha256:0405506e8b4696520104143f5d24acd1b3539c3eeea178f23d50e3c4996e082e

Observation a07ae45f-5f47-45cb-8b96-38a37e4ef862 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.496279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.496279Z digest=sha256:8e41ce7729e416a6f76ca13665bcfc10fb351cedae5afdad9a0ee7f60bd078fd

Observation 08fbaf68-d377-411b-bcb9-503108e66b55 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.795789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.501784Z digest=sha256:7186e62f9b66886d51948b24022ff766cafb362e3da164f203778a59c1bbe859

Observation 5464ffc9-266b-43db-9ef4-199cb9e1b7ad · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.778107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.508412Z digest=sha256:d1e734887c0ccedf3b5612ce3f33d99113328c78b7c0041b220669b9475befce

Observation 6f054da8-5404-4e99-9198-5b39f60e9c16 · outbound

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

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.513049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.513049Z digest=sha256:1ed76820c1b64658673069d68b11e5bea724e3504dbe2a489184b650ef152d19

Observation 67415a2a-5c38-40df-ae47-315242948a31 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.751197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.518174Z digest=sha256:4be4dcc37c589cc810ecc9a32f542cd66b55e3d28e6bc635940dcc65834bf381

Observation 1185139d-531f-4366-b4e3-22147ff1372e · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 39

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.718840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.523016Z digest=sha256:0749b61e7563d0a7f10651c746f63be27494378cbe4e96f000b3b077bb9ca67b

Observation 155fbf20-a220-44b3-a42d-44e37624ee24 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.698403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.528772Z digest=sha256:e1cd2370911a2843449d4f15c198a2056b9f6de94bbede1c3fb71355fc8025bc

Observation 19a0bbfc-2f30-4a17-8ac2-af495c3fcdda · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.681231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.533356Z digest=sha256:4843217a00916157efdecf660565f1b56e7f5846310ca2ce30e9e613b9f7287f

Observation 82792e81-439f-46ea-9e4d-0b1f1fd8e573 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.664887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.539595Z digest=sha256:e630bef04f99b5c7c1428a38bf167bc0c5a90426a7716ebada7b2d76056a30a0

Observation 75c6598e-4096-4d67-8213-229f86126856 · outbound

This paper cites Cross-modal Information Flow in Multimodal Large Language Models.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Cross-modal Information Flow in Multimodal Large Language Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.544824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.544824Z digest=sha256:8b34085450008b1d4b44f7ffddfcc615ff5a2345707eb2a4dc57b5473b444403

Observation 234a67b6-96e6-4162-9b9b-5279aae10c1b · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 44

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.643359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.551251Z digest=sha256:424823c5c3ccd777864dde8c7f775f6a92b798cd5f908ab7b5edd6f6cb56c19a

Observation 58e7eb06-5295-4bff-a282-3edde6c5ad4a · outbound

This paper cites Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.556736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.556736Z digest=sha256:d03044b50f2c6c9d32146a8c81844cddcde71eaf4c31fce2eeffee4f1b65bd1c

Observation c91a4a47-1d1b-4d1f-ae9b-22f9a910e848 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.627539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.562595Z digest=sha256:54a7db24cff522b7ca53436686310e7b731c85dc3d05fa87de6205f711436d45

Observation abf8391a-4cc4-47bd-bed3-db3c01ec31ea · outbound

This paper cites Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.567271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.567271Z digest=sha256:c6d083f991dc9017634d040127c2e7d49b5e4ec717f534acb838381013a0a49a

Observation d08e589e-5f89-48e7-8cf3-e6ba1c7f4431 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.575375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.575375Z digest=sha256:6317abb9950b401f7df2dd63f38af10c4e256fd2c990958e4fddbd1d506e40cf

Observation d13e2e16-7661-460a-a80a-41a83e2618d3 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.598229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.585880Z digest=sha256:429b97095c3df7774154038b03ee839b23ac30ae40434477721a32f7e52e7e91

Observation 5562b0a3-4e15-4b4e-ac3b-1cc377ea9bf3 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 50

Resolution
unresolved
raw_fallback, observed 2026-08-06T12:40:06.575665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.591933Z digest=sha256:329e3e3c666dbbd3e9c66cc7d3fd2927219f8cf255bbb98c48f7286f68470cbb

Observation 3ce53492-61fe-4e05-95c4-dcd88a2c16b2 · outbound

This paper cites an unresolved cited work.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Unresolved cited work

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.597046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.597046Z digest=sha256:5ddbe447376c50a838cb5545cccda60ecbc63466cda2361de675b5b49e47cc96

Observation 268f75e4-1549-4b9f-a7a7-ca6718a2f04d · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 2023

Resolution
malformed identifier
no resolver link, observed 2026-08-06T12:40:05.603091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.603091Z digest=sha256:712476aa83f3140066067eda935d68efb8a99ac29f8a75d83243838d30f1f750

Observation 47412348-8486-4c2d-9dc9-6b1e15be97fe · outbound

This paper cites In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T12:40:07.161498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T12:40:05.210676Z digest=sha256:72ca56774348a85e9088feabaddff5cae6a123a48ef769e1c4c6cd87878e60a0

Observation 7ddbf9bc-4e04-43db-921b-85cfde575da9 · outbound

This paper cites Towards Interpreting Visual Information Processing in Vision-Language Models.

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models Towards Interpreting Visual Information Processing in Vision-Language Models

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-06T12:40:05.418595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T12:40:05.418595Z digest=sha256:24553e24ab88790637a39edfce27af9e040094a24e6034aaeedb3745e35a6c40

Pith citing papers

No inbound Pith citation observations are available.