Paper Citation Record · LEDGER

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

As of 8 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2509.25533.

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

pith.paper-citation-record.v1
2509.25533 v2

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T13:45:27.971234Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

17 of 17 outbound references displayed

verified exact0
verified fuzzy0
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0288cf69-3b9f-47a9-988f-623adeb6abbc · outbound

This paper cites an unresolved cited work.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.971234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9798a55-6502-4a83-9d66-1fb0777b9aad · outbound

This paper cites How Robust is Google's Bard to Adversarial Image Attacks?.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models How Robust is Google's Bard to Adversarial Image Attacks?

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.355350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa488af9-c9f8-4af5-b05b-c8f323acbc04 · outbound

This paper cites X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.695560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55cac5bf-0221-47e5-8ed7-65393e148cbc · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.820422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b06be588-7243-45e2-a00d-d19b24ded7b8 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Steering Llama 2 via Contrastive Activation Addition

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.933234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a351771-dc91-40a1-969e-0b6c8e39baf7 · outbound

This paper cites Visual Adversarial Examples Jailbreak Aligned Large Language Models.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.025943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aef1dfde-7d44-4d8d-a5e6-2aa53e5b74fe · outbound

This paper cites Failures to Find Transferable Image Jailbreaks Between Vision-Language Models.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.114819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54bd8f24-2f21-4381-870a-fa1e1b82fc8b · outbound

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

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.193722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef1ac527-737b-4822-910a-5247718a6f87 · outbound

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

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.329648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad59e0bd-557e-4d32-8ad1-01bf5ef03063 · outbound

This paper cites Steering Language Models With Activation Engineering.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Steering Language Models With Activation Engineering

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.475815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fef9a84f-9bd2-402d-979e-78f556efb848 · outbound

This paper cites AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.597133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc3e027f-41fb-48fd-8285-5f1fd1a19a74 · outbound

This paper cites On Evaluating Adversarial Robustness of Large Vision-Language Models.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models On Evaluating Adversarial Robustness of Large Vision-Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.722293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 698190be-f818-430b-bb02-7e330f05392d · outbound

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

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:27.852811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b2fd7ac-43cd-4335-9b36-25aaee936410 · outbound

This paper cites Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.425121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebef0b59-8eb2-44e1-8a69-0e328e139d75 · outbound

This paper cites Controlling Large Language Models Through Concept Activation Vectors.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Controlling Large Language Models Through Concept Activation Vectors

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.189146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c82158bb-6354-4108-8dac-4d49dca84707 · outbound

This paper cites Image Hijacks: Adversarial Images can Control Generative Models at Runtime.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.101151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f4b8a14-b70f-41ac-8c58-79ba983a53fc · outbound

This paper cites Measuring Massive Multitask Language Understanding.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Measuring Massive Multitask Language Understanding

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.549161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.