Paper Citation Record · LEDGER

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows

As of 10 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2606.06875.

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

pith.paper-citation-record.v1
2606.06875 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T22:58:44.478077Z

measured 19 of 19 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 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

19 of 19 outbound references displayed

verified exact12
verified fuzzy0
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ef9b06b8-06ae-470c-8450-9c1190c339af · outbound

This paper cites Open Problems in Machine Unlearning for AI Safety.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Open Problems in Machine Unlearning for AI Safety

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.080835Z

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 70f4fe7d-fcdb-47e8-b603-9e0ae03bdac1 · outbound

This paper cites Trce: Towards reliable malicious concept erasure in text-to-image diffusion models.ArXiv, abs/2503.07389.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Trce: Towards reliable malicious concept erasure in text-to-image diffusion models.ArXiv, abs/2503.07389

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.075457Z

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 188fe6ad-d9bb-450a-beab-bfaf3968d3d9 · outbound

This paper cites Prompt- ing4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts.ArXiv, abs/2309.06135.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Prompt- ing4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts.ArXiv, abs/2309.06135

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.078285Z

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 794bcc62-c9f1-4579-80ab-8a00799ac7e8 · outbound

This paper cites ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.083615Z

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 e54077ec-8225-47a6-a40f-b0fb01065343 · outbound

This paper cites ImagenHub: Standardizing the evaluation of conditional image generation models.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows ImagenHub: Standardizing the evaluation of conditional image generation models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.101087Z

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 6500d7b3-fb0f-4aac-8276-d4f930ddaa2c · outbound

This paper cites FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:07:09.101268Z

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 e6512a7e-652c-43cd-876e-fb27da12b5e9 · outbound

This paper cites Crafting papers on machine learning.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Crafting papers on machine learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T22:58:44.478077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7a2adca-925c-476f-93f9-7b936434cf40 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-02T16:07:09.103542Z

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 fb6c547b-cb61-4efb-85ce-5c022e091fdf · outbound

This paper cites Modifier unlocked: Jailbreaking text-to-image models through prompts.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Modifier unlocked: Jailbreaking text-to-image models through prompts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T22:58:44.478077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0aae102-4c55-4dcd-9dc0-ad9e95f4b6b3 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-02T16:07:09.103389Z

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 ce4804bc-5012-46ae-86b3-58ab0b04dd2b · outbound

This paper cites Red-Teaming the Stable Diffusion Safety Filter.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Red-Teaming the Stable Diffusion Safety Filter

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.105956Z

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 dbd587d5-1321-46ae-9c87-49aef88e8104 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-02T16:07:09.108787Z

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 ecf3e5b9-7738-4583-b242-d8ab161ff53c · outbound

This paper cites Restricting the Flow: Information Bottlenecks for Attribution.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Restricting the Flow: Information Bottlenecks for Attribution

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T16:07:09.111801Z

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 c6c96902-ffd2-4bf5-97af-7ca9c8bea97f · outbound

This paper cites Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.093167Z

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 4750da9d-8f56-4c53-919b-9554b1f30c4d · outbound

This paper cites FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.096124Z

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 ca61de98-64b9-43f3-bec3-57f5153404d1 · outbound

This paper cites Mmdt: Decoding the trustworthiness and safety of multi- modal foundation models.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows Mmdt: Decoding the trustworthiness and safety of multi- modal foundation models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T22:58:44.478077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d37031d1-782c-4990-b3d2-993bf8868bda · outbound

This paper cites 19 Unified Safe Text-to-Image Synthesis and Image Editing in MM-DiTs Table 5.Representative prompt examples from Unsafe-1K.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows 19 Unified Safe Text-to-Image Synthesis and Image Editing in MM-DiTs Table 5.Representative prompt examples from Unsafe-1K

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-27T22:58:44.478077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e564671a-98d2-4b8f-96b4-9c791583e038 · outbound

This paper cites The RAB effectively identifies problematic prompts that bypass safety mechanisms, resulting in NSFW content generation.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows The RAB effectively identifies problematic prompts that bypass safety mechanisms, resulting in NSFW content generation

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:09.098474Z

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 60e96dd9-ea72-4cde-a857-688ddb523eb6 · outbound

This paper cites These problematic prompts are intended to evaluate the concept removal performance of image generation models.

Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows These problematic prompts are intended to evaluate the concept removal performance of image generation models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T22:58:44.478077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.