Paper Citation Record · LEDGER

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions

As of 18 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2504.21292.

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

pith.paper-citation-record.v1
2504.21292 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:13:23.656049Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

46 of 46 outbound references displayed

verified exact0
verified fuzzy31
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 43f91412-12f4-402c-b694-21aad15dec5f · outbound

This paper cites Butterworth.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Butterworth

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.966795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e7d4d3cd-aa4a-4d6e-911a-ec62119f8453 · outbound

This paper cites Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.186771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 220a54da-d045-4b39-bcaa-13504f7f157c · outbound

This paper cites Pixart-Σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Pixart-Σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.893786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 169f7757-9882-407c-b96c-0bd968dab5b0 · outbound

This paper cites Simple baselines for image restoration.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Simple baselines for image restoration

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.881518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 440b074c-1963-43e2-8844-b4f6b1ab1a7f · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.201201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ecd76a3-1904-4344-9473-7ae4d76bd0b5 · outbound

This paper cites Rifegan: Rich feature generation for text-to-image synthesis from prior knowledge.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Rifegan: Rich feature generation for text-to-image synthesis from prior knowledge

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.826809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9e648e70-1a8d-44ae-82f3-57e171ad2ce1 · outbound

This paper cites Kaplan, and Enrico Shippole.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Kaplan, and Enrico Shippole

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.766066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e65840dc-93dc-4a1b-9366-1da507335c6a · outbound

This paper cites Transformers are ssms: Generalized models and efficient algorithms through structured state space duality.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Transformers are ssms: Generalized models and efficient algorithms through structured state space duality

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.753001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3477e814-f06d-4785-829d-e2b3f3615f3c · outbound

This paper cites Taming transformers for high-resolution image synthesis.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Taming transformers for high-resolution image synthesis

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.488215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7f555d8b-8d37-4321-95c9-af2e28228302 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.222435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc921f8e-2e7f-4f71-96c6-c1639c4f77c4 · outbound

This paper cites Efficient diffu- sion training via min-snr weighting strategy.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Efficient diffu- sion training via min-snr weighting strategy

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.476244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9128077e-87c4-4fbd-84c8-1b3d9b7bab7d · outbound

This paper cites Neighborhood attention transformer.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Neighborhood attention transformer

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.357697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0e58f682-61d2-46eb-86ce-b6238bac75e0 · outbound

This paper cites Classifier-free diffusion guidance.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Classifier-free diffusion guidance

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.316049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b893b62c-f6a4-4858-a5d3-6ea4f831a3bd · outbound

This paper cites Denoising diffu- sion probabilistic models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Denoising diffu- sion probabilistic models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.292563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 276fecd5-2493-48d6-8fef-42d232e4358d · outbound

This paper cites Alias-free generative adversarial networks.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Alias-free generative adversarial networks

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.234747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dc756dc6-b5a3-493c-b60f-4c5aff047ddb · outbound

This paper cites Elucidating the design space of diffusion-based generative models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Elucidating the design space of diffusion-based generative models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.188853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0df50b9b-cae6-40b6-abb7-9f8afa36dd61 · outbound

This paper cites Analyzing and improving the training dynamics of diffusion models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Analyzing and improving the training dynamics of diffusion models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:25.177483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c1d3fd5d-3da1-48e3-b490-3f3eba1f5e13 · outbound

This paper cites an unresolved cited work.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:13:25.165990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ed7de0cd-bf6a-4282-b846-6cf3b8ffe322 · outbound

This paper cites an unresolved cited work.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:13:24.990278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2a2049d4-7da3-4801-a954-26c1e83f79c0 · outbound

This paper cites Faster Diffusion via Temporal Attention Decomposition.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Faster Diffusion via Temporal Attention Decomposition

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.342919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ce73f91-59b4-402d-b201-ec65c663fcb5 · outbound

This paper cites LinFusion: 1 GPU, 1 Minute, 16K Image.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions LinFusion: 1 GPU, 1 Minute, 16K Image

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.346402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01f18ee4-3953-4363-bca3-0481593350fc · outbound

This paper cites More Control for Free! Image Synthesis with Semantic Diffusion Guidance.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions More Control for Free! Image Synthesis with Semantic Diffusion Guidance

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.400547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f33a93-d365-4541-8bdb-b352ccbbbc7f · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Swin transformer: Hierarchical vision transformer using shifted windows

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.977269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 802b7057-62c9-4fdc-9369-eaf4b656c76c · outbound

This paper cites Token caching for diffusion transformer acceleration.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Token caching for diffusion transformer acceleration

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.467486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7197f8be-b6cb-47d8-b49d-0f910cb3ef38 · outbound

This paper cites DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.478064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 313f2e72-1254-4b13-b288-9f7b931c9127 · outbound

This paper cites Understanding the effective receptive field in deep convolu- tional neural networks.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Understanding the effective receptive field in deep convolu- tional neural networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.909520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3f35b6bf-8c54-48d5-a74c-a2a3273b5b27 · outbound

This paper cites Kingma, Stefano Ermon, Jonathan Ho, and Tim Salimans.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Kingma, Stefano Ermon, Jonathan Ho, and Tim Salimans

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.796516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0c64192b-3673-4ed4-b1b7-c66a021043c2 · outbound

This paper cites GLIDE: towards photorealistic image gen- eration and editing with text-guided diffusion models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions GLIDE: towards photorealistic image gen- eration and editing with text-guided diffusion models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.783837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e388da6e-fc73-4bbc-ab5e-6d73dff89b34 · outbound

This paper cites an unresolved cited work.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:13:24.698053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 040c90cb-ab5f-4c65-adbb-043919e320f1 · outbound

This paper cites Scalable diffusion models with transformers.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Scalable diffusion models with transformers

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.610380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1f5361bb-6d0f-4b23-9c71-7a5fe37ed309 · outbound

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

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.498577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e177a634-6f2c-4dd4-91ea-a04dbae4060b · outbound

This paper cites Proakis and Dimitris G.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Proakis and Dimitris G

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.599543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4ada7950-00d7-4029-86d5-61379ccc04e1 · outbound

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

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions High-resolution image synthesis with latent diffusion models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.471349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d6c679d-5c39-44c9-90d8-a29cd4d030c9 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions U-net: Convolutional networks for biomedical image segmentation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.460101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cb1efbf7-1a4d-4add-8d42-1bac940b4e41 · outbound

This paper cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.516270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0402eedd-cd4d-4700-bfb4-7ab1194bf52a · outbound

This paper cites Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.448438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5316c712-2f78-461b-a5b7-49061dc37d3e · outbound

This paper cites Laion-5b: A large-scale dataset for training ai models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Laion-5b: A large-scale dataset for training ai models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.409166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aceb1237-0934-4799-880e-361589e470fe · outbound

This paper cites FORA: Fast-Forward Caching in Diffusion Transformer Acceleration.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions FORA: Fast-Forward Caching in Diffusion Transformer Acceleration

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T05:13:23.602018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06d5847f-c57a-4677-a417-f2782a359fe2 · outbound

This paper cites Denoising diffusion implicit models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Denoising diffusion implicit models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.383639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4d3724bb-943a-4a00-a707-cbcc5c8072b7 · outbound

This paper cites Kingma, Ab- hishek Kumar, Stefano Ermon, and Ben Poole.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Kingma, Ab- hishek Kumar, Stefano Ermon, and Ben Poole

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.373164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fadae87b-05bb-47df-b0bc-1a559cbd99cf · outbound

This paper cites Expos- ing flaws of generative model evaluation metrics and their unfair treatment of diffusion models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Expos- ing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.360969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 28217a4f-e2fc-4163-a21f-bae3f5197bd8 · outbound

This paper cites Rethinking the incep- tion architecture for computer vision.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Rethinking the incep- tion architecture for computer vision

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.297407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8a4571b2-d12c-44a4-a198-c91a29bdb008 · outbound

This paper cites text2image-multi-prompt: A multi-prompt dataset for text-to-image generation.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions text2image-multi-prompt: A multi-prompt dataset for text-to-image generation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.274251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b0c7b602-70d8-4380-82dd-ab6acfa35708 · outbound

This paper cites Attention is all you need.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Attention is all you need

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.192012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dfeb0648-83c3-4146-9757-7b50c9b77d56 · outbound

This paper cites midjourney-v5-202304-clean.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions midjourney-v5-202304-clean

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.103327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c6cdd0fa-bf29-46d7-8663-a87e6a4ae62c · outbound

This paper cites Ditfastattn: Attention compression for diffusion transformer models.

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions Ditfastattn: Attention compression for diffusion transformer models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:13:24.091649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

No inbound Pith citation observations are available.