Paper Citation Record · LEDGER

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

As of 11 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 1 inbound Pith citation observation for arXiv:2606.08063.

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

pith.paper-citation-record.v1
2606.08063 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T20:06:11.170282Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:24:56.314750Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T00:24:59.515690Z

Reference resolution

15 of 15 outbound references displayed

verified exact5
verified fuzzy0
unresolved7
parse uncertain0
malformed identifier2
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 04d0cf82-0ed9-45c2-b3e6-816187139f14 · outbound

This paper cites Thinking with Generated Images.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Thinking with Generated Images

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:47:23.363872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6413f259-6bb7-404b-8c2d-47c9b8ff1903 · outbound

This paper cites Emerging Properties in Unified Multimodal Pretraining.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Emerging Properties in Unified Multimodal Pretraining

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:47:23.361873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37c7254b-b6ff-4396-b616-26831337570d · outbound

This paper cites A semantic decoupling-based two-stage rainy-day attack for revealing weather robustness de- ficiencies in vision-language models.arXiv preprint arXiv:2601.13238,.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? A semantic decoupling-based two-stage rainy-day attack for revealing weather robustness de- ficiencies in vision-language models.arXiv preprint arXiv:2601.13238,

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:47:23.366793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e2805914-94f6-4d9c-a815-de53085a6ee6 · outbound

This paper cites When mllms meet compression distortion: A coding paradigm tailored to mllms.arXiv preprint arXiv:2509.24258, 2025a.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? When mllms meet compression distortion: A coding paradigm tailored to mllms.arXiv preprint arXiv:2509.24258, 2025a

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:47:23.372532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eb35a530-d515-4c1e-90cd-e770e679bed9 · outbound

This paper cites Qwen3 Technical Report.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Qwen3 Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:47:23.370481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 97513ecf-ab47-4929-b61f-0004d92d50f4 · outbound

This paper cites DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-02T20:47:23.372882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 78585909-07de-4cff-8f90-d642e31151cd · outbound

This paper cites an unresolved cited work.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95b7a6c7-845f-43b5-83e8-58ab4c9dba1c · outbound

This paper cites an unresolved cited work.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 047355cf-e92e-4cb7-aca3-b87e692c261c · outbound

This paper cites The aggregate performance is represented by the mean score: Score= 1 N NX i=1 si,(12) where si denotes the scoring result assigned by GPT-3.5-turbo for the i-th sample.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? The aggregate performance is represented by the mean score: Score= 1 N NX i=1 si,(12) where si denotes the scoring result assigned by GPT-3.5-turbo for the i-th sample

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f681bb66-1a7a-4b56-a689-a0ce8f70bfb2 · outbound

This paper cites restoration → understanding.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? restoration → understanding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 537c45d4-85bf-426b-bf1c-5f217a7bff83 · outbound

This paper cites 0.7398 for Robust-U1.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? 0.7398 for Robust-U1

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c47499-70a3-4c76-82b8-7d50da437c3d · outbound

This paper cites Rec. Mem.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Rec. Mem

Reference 12

Resolution: malformed identifier; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1441b64-924d-4553-b435-5c99c677b290 · outbound

This paper cites an unresolved cited work.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd02ebba-dd69-4238-9232-c363fa1c9a2c · outbound

This paper cites Table 18.Sensitivity ofRobust-U1’s scores on R-Bench to the choice of LLM-based evaluator.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Table 18.Sensitivity ofRobust-U1’s scores on R-Bench to the choice of LLM-based evaluator

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6375af0-43b5-4020-873d-7e96cbcad9da · outbound

This paper cites Limitations and Future Work H.1.

Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Limitations and Future Work H.1

Reference 15

Resolution: malformed identifier; no resolver link, observed 2026-06-27T20:06:11.170282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0464cdaa-f98e-415b-8a4b-bb7e711aa8ab · inbound

Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning cites this paper.

Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-06T00:24:59.620204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.