Paper Citation Record · LEDGER

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse

As of 20 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2607.15650.

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

pith.paper-citation-record.v1
2607.15650 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T22:45:29.345624Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

40 of 40 outbound references displayed

verified exact0
verified fuzzy0
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0785c1fc-e7a5-48c1-b2e0-82f591982cf1 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.252723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b77b0f2-a4f8-4831-ba01-cead1045f4cc · outbound

This paper cites $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.317086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41dc6617-397b-4161-bee6-091be9d98645 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.403139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6650e77c-3412-4d40-b0e7-98a427856fe7 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.493412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 924b22e3-d343-4e3e-b69f-4dbfa0eb1369 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.549468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd95a0f4-267f-40a8-aa4d-7bf3fd4fb891 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.629983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb51fa9a-23e3-4dec-9c0e-c2db2c355413 · outbound

This paper cites xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.749375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d4c530a-dd79-45c6-a0f3-14a7acad574b · outbound

This paper cites USP: A Unified Sequence Parallelism Approach for Long Context Generative AI.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse USP: A Unified Sequence Parallelism Approach for Long Context Generative AI

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.808153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea0e8ef-55d6-427a-9f61-ce1736aaf4e4 · outbound

This paper cites Classifier-Free Diffusion Guidance.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Classifier-Free Diffusion Guidance

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:25.938056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1acd64b-2edf-402e-9aa1-10c311778b1f · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.029274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 823fe407-83d4-408b-9867-35590549321e · outbound

This paper cites DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.151258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 522be9f6-7eb7-4ae9-8721-97b4821178fd · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.247410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2daaa9a3-34e2-418f-90dc-9a828ed67add · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.334984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4ef2632-5e87-46bc-bc7f-c84146a0ae1b · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.393600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65fd817b-e886-4c5e-947a-82f23374cf2c · outbound

This paper cites Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.485433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a35f0e22-eaf8-47c9-865c-2e8d216bcb01 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.623924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24baaa29-e874-4d57-9223-ca2b568df412 · outbound

This paper cites Ring Attention with Blockwise Transformers for Near-Infinite Context.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Ring Attention with Blockwise Transformers for Near-Infinite Context

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.707814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b84851b-9f73-4e9d-a4ba-60fbd5dac9a0 · outbound

This paper cites From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.772478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac6811c-c5f4-4bbe-b6ad-e3bc289802e9 · outbound

This paper cites Rectified Flow: A Marginal Preserving Approach to Optimal Transport.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Rectified Flow: A Marginal Preserving Approach to Optimal Transport

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:26.945866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4199c132-968a-48cf-9678-9358b7234195 · outbound

This paper cites Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:27.121517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d2dd36-afec-4d65-9b70-5e6a87ecde36 · outbound

This paper cites Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:27.256030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0727de2e-b146-47cc-bd53-6021b9c43f9e · outbound

This paper cites On Distillation of Guided Diffusion Models.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse On Distillation of Guided Diffusion Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:27.373202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84ffb4cd-1019-4db1-a9c9-7a748eb638fd · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:27.490719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88e68ee6-9952-4054-aae9-6f0c6d258ffa · outbound

This paper cites Adversarial Diffusion Distillation.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Adversarial Diffusion Distillation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:27.609289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c22f3dd-7284-4db1-9069-3a3da6a46509 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:27.759104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73764ea4-555e-4c5a-815a-98660f1ea44a · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:27.885554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26bdcf4f-a8e3-473d-9d9e-67213e030f15 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.032092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86f2a7f1-74c0-4112-a00d-e08afd72eabf · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Wan: Open and Advanced Large-Scale Video Generative Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.196829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25bafc31-e923-4e2b-90d5-2299483e9d8e · outbound

This paper cites PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.303227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96c6444f-561d-4539-8dc0-c48ba40df209 · outbound

This paper cites Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.423325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6096c1b9-6c77-4aea-8d38-1054b820ae48 · outbound

This paper cites Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.569375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d48df929-37f8-46fb-abf9-411ddcafd6f1 · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.734096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d9e994d-8ca0-434c-9b33-0c659e0457cf · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.798334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24f41269-918d-4045-96d7-6fe800a4b166 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.862029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8834e000-ce11-4c19-bfa2-b33c909a3594 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:28.927399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0892b896-4e8a-49c0-9b72-4599f850e8f5 · outbound

This paper cites an unresolved cited work.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:29.119025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c52120e-7eac-466c-b8d0-9e8c63940eba · outbound

This paper cites DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:29.193762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dafe89c-a4cc-4487-9aa1-3e3919d928b3 · outbound

This paper cites Real-Time Video Generation with Pyramid Attention Broadcast.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse Real-Time Video Generation with Pyramid Attention Broadcast

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:29.268782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13335d1f-be6c-499b-876e-630139f65520 · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse SGLang: Efficient Execution of Structured Language Model Programs

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:29.345624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 907a84bd-3dab-4a24-b786-11e9ce0ad3d2 · outbound

This paper cites InInternational Conference on Machine Learning (ICML).

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse InInternational Conference on Machine Learning (ICML)

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T22:45:29.020251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.