Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-21T15:09:25.818449Z
Paper Citation Record · LEDGER
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
As of 22 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 2 inbound Pith citation observations for arXiv:2601.21531.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-03T02:57:48.018700Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
27 of 27 outbound references displayed
- verified exact9
- verified fuzzy7
- unresolved7
- parse uncertain0
- malformed identifier2
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 1ab3c746-1fe9-4f79-9ad6-5ffedd4bbbb0 · outbound
This paper cites Qwen2.5-VL Technical Report.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Qwen2.5-VL Technical Report
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-21T15:10:16.503841Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation fa6fc2fc-95c7-4f4f-a501-fdb244ebeeb3 · outbound
This paper cites MobileVLM V2: Faster and Stronger Baseline for Vision Language Model.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T15:10:16.499228Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation e49eea97-df3d-4f89-bd72-36e15061fbb6 · outbound
This paper cites Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T15:10:16.531308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation e58a8779-ded4-4e44-bd60-a10d6cf7858d · outbound
This paper cites Attention score is not all you need for token importance indicator in KV cache reduction: Value also matters.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Attention score is not all you need for token importance indicator in KV cache reduction: Value also matters
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T15:10:16.871354Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 6b7f4381-3e20-4537-91f1-a7c5dd1323ac · outbound
This paper cites Vision-language-action models for autonomous driving: Past, present, and future.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Vision-language-action models for autonomous driving: Past, present, and future
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T15:10:16.526862Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation dcff0bad-9c40-47ae-9458-c26b0d523365 · outbound
This paper cites Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T15:10:16.490773Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 3257afd3-1b64-4f74-9467-fd0074446b5d · outbound
This paper cites Veattack: Downstream-agnostic vision encoder attack against large vision language models.arXiv preprint arXiv:2505.17440.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Veattack: Downstream-agnostic vision encoder attack against large vision language models.arXiv preprint arXiv:2505.17440
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T15:10:16.535977Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 7a2c1145-ecb1-4827-a1f7-4cc35667a8b4 · outbound
This paper cites GPT-4 Technical Report.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression GPT-4 Technical Report
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T15:10:16.512926Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a29f7e4e-2710-4979-b29a-f9bdd6c7b702 · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Gemini: A Family of Highly Capable Multimodal Models
Reference 9
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-21T15:10:16.494936Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation d8727c11-feb6-4cbd-bec3-549c82636662 · outbound
This paper cites InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T15:10:16.508674Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation ad7e7783-28dd-46a0-9d18-a5d965129a95 · outbound
This paper cites Mobile-Agent-v3: Fundamental Agents for GUI Automation.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Mobile-Agent-v3: Fundamental Agents for GUI Automation
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T15:10:16.521668Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 0a5eb920-a160-47af-978a-633c1499df6c · outbound
This paper cites DART: Dif- ferentiable dynamic adaptive region tokenizer for vision foundation models.arXiv preprint arXiv:2506.10390.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression DART: Dif- ferentiable dynamic adaptive region tokenizer for vision foundation models.arXiv preprint arXiv:2506.10390
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T15:10:16.517475Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a313bdb6-e182-4d5b-adfa-07998bc26ea6 · outbound
This paper cites AppAgent: Multimodal agents as smartphone users.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression AppAgent: Multimodal agents as smartphone users
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T15:10:16.887535Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation c11f1702-528a-48fd-a5f8-07f9f5dc434e · outbound
This paper cites ② Outer-LLMapproaches perform token selection or aggregationbeforethe main language model computation, treating the LLM as a black box.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression ② Outer-LLMapproaches perform token selection or aggregationbeforethe main language model computation, treating the LLM as a black box
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T15:10:16.868416Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation d83d6d59-0837-4feb-bb19-383c93bb349a · outbound
This paper cites A” and “S.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression A” and “S
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T15:10:16.882328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 2be79474-60ac-4954-b1dc-af9c94a63f6c · outbound
This paper cites an unresolved cited work.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T15:10:16.879070Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 350ca5d7-013f-4d99-b260-7c4f82e622f4 · outbound
This paper cites an unresolved cited work.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Unresolved cited work
Reference 17
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T15:10:16.890142Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation cd59b761-8129-4356-b5bb-b749c6ac37a7 · outbound
This paper cites an unresolved cited work.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Unresolved cited work
Reference 18
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T15:10:16.884875Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation d178112d-52c2-4e50-91f7-d5aff6161765 · outbound
This paper cites an unresolved cited work.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Unresolved cited work
Reference 19
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T15:10:16.865543Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 33eeca9c-fc58-40e3-91dc-b32edb71a9a2 · outbound
This paper cites an unresolved cited work.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T15:10:16.892636Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation c37b96d3-f8e9-498e-8816-9f35a383bbd4 · outbound
This paper cites an unresolved cited work.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T15:10:16.900935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation e5f01081-b786-494d-b3ea-d9cd256148e0 · outbound
This paper cites For prompt-diverse tasks such as VQA, VEAttack (Mei et al.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression For prompt-diverse tasks such as VQA, VEAttack (Mei et al
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T15:10:16.895308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 7e5a2e41-f3fd-4873-8cbf-f2704946f340 · outbound
This paper cites Compared to open-ended VQA, GQA emphasizes systematic generalization and relational grounding.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Compared to open-ended VQA, GQA emphasizes systematic generalization and relational grounding
Reference 23
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-21T15:10:16.898296Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 9376ec39-d2e4-4335-b692-55e060fe9cb8 · outbound
This paper cites It utilizes vision-encoder attention maps to estimate token importance, identifying and retaining a compact subset of highly informative tokens.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression It utilizes vision-encoder attention maps to estimate token importance, identifying and retaining a compact subset of highly informative tokens
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T15:10:16.903881Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 5aec3930-533a-488f-8b85-9a764d368930 · outbound
This paper cites Importantly, most non-zero λ settings are comparable to or better thanλ=0, indicating that incorporating RDA is generally beneficial even without delicate tuning.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Importantly, most non-zero λ settings are comparable to or better thanλ=0, indicating that incorporating RDA is generally beneficial even without delicate tuning
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T15:10:16.873954Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a1b9f1fe-a914-4f29-ad06-ba85004cd42c · outbound
This paper cites peakiness.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression peakiness
Reference 26
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-21T15:10:16.906565Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation c8cab823-9227-4959-8360-1aaadf0b426d · outbound
This paper cites an unresolved cited work.
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression Unresolved cited work
Reference 27
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T15:10:16.876443Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Pith citing papers
Observation 59e09af0-3610-4134-94b5-221551f39e13 · inbound
Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models cites this paper.
Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
Reference 74
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T02:57:48.018700Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 27a920ce-8ccf-4bf7-aab9-20ad969a8772 · inbound
Visual Token Compression Enhances Robustness of MLLMs cites this paper.
Visual Token Compression Enhances Robustness of MLLMs On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
Reference 80
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T13:10:37.695997Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.