Paper Citation Record · LEDGER

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers

As of 10 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2512.16615.

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

pith.paper-citation-record.v1
2512.16615 v2

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T15:35:17.596078Z

measured 43 of 43 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

43 of 43 outbound references displayed

verified exact0
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 67a6f03d-8ad4-450c-a056-0638d32f6739 · outbound

This paper cites Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:13.213540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c217c85-25fb-41a1-a626-ff52e4422d43 · outbound

This paper cites PixelFlow: Pixel-Space Generative Models with Flow.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers PixelFlow: Pixel-Space Generative Models with Flow

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:13.368010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7031c64-1827-49c9-97a3-7a4a7fb8921e · outbound

This paper cites On the Importance of Noise Scheduling for Diffusion Models.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers On the Importance of Noise Scheduling for Diffusion Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:13.540081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd7768e-925c-44e9-93a3-a84b59a1b181 · outbound

This paper cites Scalable high-resolution pixel-space image syn- thesis with hourglass diffusion transformers.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Scalable high-resolution pixel-space image syn- thesis with hourglass diffusion transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:13.653021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d715900-2980-43f3-9959-899de6adbaef · outbound

This paper cites FlashAttention-2: Faster attention with better par- allelism and work partitioning.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers FlashAttention-2: Faster attention with better par- allelism and work partitioning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:13.809650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70490a8b-271d-4fa7-a109-4eb20bb9c319 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344–16359, 2022.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Flashattention: Fast and memory-efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344–16359, 2022

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:13.940097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f62f618-a650-40cf-ad9e-e30b5d61dfb7 · outbound

This paper cites Scaling vision transformers to 22 billion pa- rameters.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Scaling vision transformers to 22 billion pa- rameters

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.085627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335ee7a3-0baa-4d9f-8517-6c0ef167ad64 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Imagenet: A large-scale hierarchical image database

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.191205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2474dff8-fb2b-4a03-9acf-3b0cb01ad7fc · outbound

This paper cites Scaling recti- fied flow transformers for high-resolution image synthesis.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.299211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 000c4cf3-3be2-46c5-aea4-c68bba4c22e8 · outbound

This paper cites Log-linear attention.arXiv preprint arXiv:2506.04761, 2025.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Log-linear attention.arXiv preprint arXiv:2506.04761, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.381463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b28721a1-a70c-49be-8199-a1736b3abcff · outbound

This paper cites Two fast algorithms for sparse matri- ces: Multiplication and permuted transposition.ACM Trans- actions on Mathematical Software (TOMS), 4(3):250–269,.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Two fast algorithms for sparse matri- ces: Multiplication and permuted transposition.ACM Trans- actions on Mathematical Software (TOMS), 4(3):250–269,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.447712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f45b1042-0927-47b3-b087-6e3f81b5e2b3 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilib- rium.Advances in neural information processing systems, 30, 2017.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Gans trained by a two time-scale update rule converge to a local nash equilib- rium.Advances in neural information processing systems, 30, 2017

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.538916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87f02fc8-e78e-4ac5-9b55-1a524a36b879 · outbound

This paper cites sim- ple diffusion: End-to-end diffusion for high resolution im- ages.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers sim- ple diffusion: End-to-end diffusion for high resolution im- ages

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.620080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9affbbef-ecf8-41d0-a477-0e26e366953c · outbound

This paper cites Minference 1.0: Accel- erating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Sys- tems, 37:52481–52515, 2024.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Minference 1.0: Accel- erating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Sys- tems, 37:52481–52515, 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.718651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7b3369c-9950-46f7-8e6d-8b3269b475c7 · outbound

This paper cites Fast mul- tipole attention: A divide-and-conquer attention mechanism for long sequences.arXiv preprint arXiv:2310.11960, 2023.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Fast mul- tipole attention: A divide-and-conquer attention mechanism for long sequences.arXiv preprint arXiv:2310.11960, 2023

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.839017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae2aa1bf-6511-467a-9f75-b3024ce4633f · outbound

This paper cites A style-based generator architecture for generative adversarial networks.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers A style-based generator architecture for generative adversarial networks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:14.997239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a12aa9b4-e674-405f-b4e7-b98ea22ddcd9 · outbound

This paper cites Reformer: The Efficient Transformer.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Reformer: The Efficient Transformer

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.125441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbcd84db-289e-4cb0-89a8-1a026b335335 · outbound

This paper cites Flux.https://github.com/ black-forest-labs/flux, 2023.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Flux.https://github.com/ black-forest-labs/flux, 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.202397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81202b2c-1ae7-4f0b-a702-3c378829a48e · outbound

This paper cites Radial attention: O (nlog n) sparse at- tention with energy decay for long video generation.arXiv preprint arXiv:2506.19852, 2025.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Radial attention: O (nlog n) sparse at- tention with energy decay for long video generation.arXiv preprint arXiv:2506.19852, 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.224825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 713ac270-da36-4af1-bfe3-1fbe0720a430 · outbound

This paper cites Flow Matching for Generative Modeling.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Flow Matching for Generative Modeling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.339991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7500125-8856-46fe-8513-69c861dde2d5 · outbound

This paper cites Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.447360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f28409e-6f4e-4de5-a9df-3a649259673c · outbound

This paper cites MoBA: Mixture of Block Attention for Long-Context LLMs.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers MoBA: Mixture of Block Attention for Long-Context LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.553731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 775d61ef-fa8c-40ee-8185-c4fffa423b47 · outbound

This paper cites SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.656310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e5d6264-4f8e-4682-b607-e1f9d25a0775 · outbound

This paper cites Merge-based parallel sparse matrix-vector multiplication.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Merge-based parallel sparse matrix-vector multiplication

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.763826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdcbddda-8fdd-4122-b67e-de621c4d1bd2 · outbound

This paper cites Scalable diffusion models with transformers.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Scalable diffusion models with transformers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.874043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e45a4436-525a-4b80-978d-d5f563fd9044 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers High-resolution image synthesis with latent diffusion models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:15.979132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74c6f5d1-e03c-46b0-902d-84db6dd6eeb9 · outbound

This paper cites Improved techniques for training gans.Advances in neural information processing systems, 29, 2016.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Improved techniques for training gans.Advances in neural information processing systems, 29, 2016

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.041357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f27e67b0-95f3-43ef-b4a9-ab9a61620e28 · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063,.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.143178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f88dab63-130e-4143-aabf-5380e6b97bf4 · outbound

This paper cites Tri- ton: an intermediate language and compiler for tiled neu- ral network computations.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Tri- ton: an intermediate language and compiler for tiled neu- ral network computations

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.260490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 664399a5-5103-4d77-aad3-ea635ea26ced · outbound

This paper cites Attention is all you need.Advances in Neural Information Processing Systems, 2017.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Attention is all you need.Advances in Neural Information Processing Systems, 2017

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.346084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2396d55c-21f8-47ca-a969-fb5d57cafae9 · outbound

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

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Wan: Open and Advanced Large-Scale Video Generative Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.439344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3017fb52-3e51-4049-b692-27ebbccb4ef8 · outbound

This paper cites Pixnerd: Pixel neural field diffusion.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Pixnerd: Pixel neural field diffusion

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.538198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 866ffe94-0c5a-40de-8302-36b2bc19ffb7 · outbound

This paper cites VMoBA: Mixture-of-Block Attention for Video Diffusion Models.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.608595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ebcfb7-2543-4843-82e6-59217e08f0c9 · outbound

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

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.759708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d1f1a1-960b-4699-b5ba-214226e5b2c0 · outbound

This paper cites Training-free and Adaptive Sparse Attention for Efficient Long Video Generation.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Training-free and Adaptive Sparse Attention for Efficient Long Video Generation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.866211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3549f437-ce7f-46d8-b83a-21050beea9c6 · outbound

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

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:16.997670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2edf129-e399-4779-abd9-6bca243cc9af · outbound

This paper cites Native sparse attention: Hardware-aligned and natively trainable sparse attention.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Native sparse attention: Hardware-aligned and natively trainable sparse attention

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:17.154046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31dd32d6-2a34-49fc-bfc3-fe38b1a44393 · outbound

This paper cites Multi resolution analysis (mra) for approx- imate self-attention.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Multi resolution analysis (mra) for approx- imate self-attention

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:17.285937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a024c2a-442c-43b9-8f61-89f51d1338b3 · outbound

This paper cites Spargeattention: Accurate and training-free sparse attention accelerating any model in- ference.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Spargeattention: Accurate and training-free sparse attention accelerating any model in- ference

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:17.418735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d384bb83-583a-4ce1-8c3b-1351f22b83e9 · outbound

This paper cites Gonzalez, Jun Zhu, and Jianfei Chen.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Gonzalez, Jun Zhu, and Jianfei Chen

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:17.584594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9682e47-3ae1-4401-ac5e-a4e7b6f4f355 · outbound

This paper cites 11 Faster video diffusion with trainable sparse attention.arXiv e-prints, pages arXiv–2505, 2025.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers 11 Faster video diffusion with trainable sparse attention.arXiv e-prints, pages arXiv–2505, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:17.589675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61bea913-2e47-444b-ac86-ee033d622e8a · outbound

This paper cites Training-free efficient video generation via dynamic token carving.arXiv preprint arXiv:2505.16864, 2025.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers Training-free efficient video generation via dynamic token carving.arXiv preprint arXiv:2505.16864, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:17.592902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb077dba-465d-4737-a4c2-e76532465908 · outbound

This paper cites H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences.

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T15:35:17.596078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.