Paper Citation Record · LEDGER

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

As of 8 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 8 inbound Pith citation observations for arXiv:2505.14687.

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

pith.paper-citation-record.v1
2505.14687 v1

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:33:12.833852Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T06:40:16.892454Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T13:45:46.109771Z

Reference resolution

59 of 59 outbound references displayed

verified exact0
verified fuzzy23
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1aee1501-f069-4741-a986-6b2df5d8ef2a · outbound

This paper cites All are worth words: A vit backbone for diffusion models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers All are worth words: A vit backbone for diffusion models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:08.008274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79c19ce1-eb41-4073-bc28-c88e517ff778 · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:08.118350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 570f195f-2620-41dc-914c-3d3c2f7f226a · outbound

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

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Pixart- σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:18.248784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8e1e9712-4957-4e21-bf0d-88a4e3ac9617 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:08.290073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3978d47-c442-4331-bc50-de86e6ed8d5d · outbound

This paper cites COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:08.388520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b65944f0-5ef0-4d1f-90ca-b981e5a77b81 · outbound

This paper cites Flex Attention: A Programming Model for Generating Optimized Attention Kernels.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Flex Attention: A Programming Model for Generating Optimized Attention Kernels

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:08.466620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55148d36-2d75-4aad-8792-03b2310999da · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers An image is worth 16x16 words: Transformers for image recognition at scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:08.532943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ed792c8-8bfc-49e3-a976-f12d51407e7b · outbound

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

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Scaling rectified flow transformers for high-resolution image synthesis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:08.640437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c084b80d-dd89-4d79-a5c9-8a0a46f8ebde · outbound

This paper cites Structural pruning for diffusion models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Structural pruning for diffusion models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:18.103909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation aa39bbf9-2236-4de0-b5dd-b96f1eddd47d · outbound

This paper cites Geneval: An object-focused framework for evaluating text-to-image alignment.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Geneval: An object-focused framework for evaluating text-to-image alignment

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:17.981770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4b10cff7-cce4-4bf4-a41e-21bfe2969bf6 · outbound

This paper cites Neighborhood attention transformer.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Neighborhood attention transformer

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:17.816114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0eea724e-96ed-45c3-81e6-87c7c20ea960 · outbound

This paper cites A Simple Video Segmenter by Tracking Objects Along Axial Trajectories.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers A Simple Video Segmenter by Tracking Objects Along Axial Trajectories

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T15:33:13.584587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 03515be4-1de5-4509-b57b-0eb2ae6b54e8 · outbound

This paper cites Flowtok: Flowing seamlessly across text and image tokens.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Flowtok: Flowing seamlessly across text and image tokens

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.065536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03e5c20f-ce90-4244-ba60-26c8237e3e2f · outbound

This paper cites Masked autoencoders are scalable vision learners.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Masked autoencoders are scalable vision learners

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.139544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 788e1d04-561d-4298-ba60-ebb3ee82799e · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Gans trained by a two time-scale update rule converge to a local nash equilibrium

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.231873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37d84659-5348-4166-a3cf-c3936698a787 · outbound

This paper cites Denoising diffusion probabilistic models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Denoising diffusion probabilistic models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.321274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f4363f6-381f-42b0-a7ea-d36456e50415 · outbound

This paper cites Vbench: Comprehensive benchmark suite for video generative models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Vbench: Comprehensive benchmark suite for video generative models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.415489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d74470f6-32c6-427b-9b13-b484f376cc39 · outbound

This paper cites BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.528176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a26b896-c5e6-445e-8391-19d4a2ddce8e · outbound

This paper cites Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.611097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1787af12-90c5-4b72-9f49-63638d80ea82 · outbound

This paper cites Auto-encoding variational bayes.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Auto-encoding variational bayes

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:17.450202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d75af1e5-a66f-4b6b-97b7-02db52c580e4 · outbound

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

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:09.802048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2bb5ecf-4d31-43cb-8817-516329cc1819 · outbound

This paper cites Flux: Official inference repository for flux.1 models, 2024.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Flux: Official inference repository for flux.1 models, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:17.223842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9cc94751-2b32-4437-b9e8-535fa9d70074 · outbound

This paper cites Set transformer: A framework for attention-based permutation-invariant neural networks.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Set transformer: A framework for attention-based permutation-invariant neural networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:17.040318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f2caf802-0014-48e2-b3de-918c4742d692 · outbound

This paper cites Koala: Empirical lessons toward memory-efficient and fast diffusion models for text-to-image synthesis.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Koala: Empirical lessons toward memory-efficient and fast diffusion models for text-to-image synthesis

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.801008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d5ca0487-ccd4-49f5-ae78-14d7505d2ada · outbound

This paper cites Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.117315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a90d978-d06c-48d5-b03f-3b411c00ea1b · outbound

This paper cites Q-diffusion: Quantizing diffusion models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Q-diffusion: Quantizing diffusion models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.609258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b92128ce-cfe6-4f37-9d28-195864e60914 · outbound

This paper cites Microsoft coco: Common objects in context.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Microsoft coco: Common objects in context

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.217019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972035e3-7f4a-4f27-92ca-ed1145ceb719 · outbound

This paper cites Flow matching for generative modeling.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Flow matching for generative modeling

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.438238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0f3c9bf9-39e8-4cd3-8cf7-717e30be88b4 · outbound

This paper cites Pseudo numerical methods for diffusion models on manifolds.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Pseudo numerical methods for diffusion models on manifolds

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.268542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0cd2cb5c-2199-4a34-a237-179c20409316 · outbound

This paper cites Alleviating distortion in image generation via multi-resolution diffusion models and time-dependent layer normalization.NeurIPS, 2024.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Alleviating distortion in image generation via multi-resolution diffusion models and time-dependent layer normalization.NeurIPS, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.093310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 19652a10-b693-4a25-877e-120a4bd9af9c · outbound

This paper cites Revision: High-quality, low-cost video generation with explicit 3d physics modeling for complex motion and interaction.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Revision: High-quality, low-cost video generation with explicit 3d physics modeling for complex motion and interaction

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.485556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b85fd9-8839-4faa-a332-90f6e4ea280d · outbound

This paper cites CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.540296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4577a30-29a3-43a2-9d6c-eab7419c672d · outbound

This paper cites Flow straight and fast: Learning to generate and transfer data with rectified flow.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Flow straight and fast: Learning to generate and transfer data with rectified flow

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.610639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d94bc75-79ca-4c30-a430-b229abadc9d4 · outbound

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

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Swin transformer: Hierarchical vision transformer using shifted windows

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.696982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dbe9e44-1332-4068-bf74-324f3776c0db · outbound

This paper cites Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:15.882654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f3338114-3ca9-4c04-8fe0-8ad611cde28c · outbound

This paper cites Pytorch: An imperative style, high-performance deep learning library.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Pytorch: An imperative style, high-performance deep learning library

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.831193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86184171-4eff-455c-bce7-036aa8a98720 · outbound

This paper cites Scalable diffusion models with transformers.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Scalable diffusion models with transformers

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.906479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 043dafce-3774-4c63-ac1a-3847466d5983 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Learning transferable visual models from natural language supervision

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.970631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a275f21e-61a1-43de-8f5a-b6f5a8de9e99 · outbound

This paper cites Stand-alone self-attention in vision models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Stand-alone self-attention in vision models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:15.688154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2bbd127e-dbbb-433b-813f-e49370cc231c · outbound

This paper cites Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.114818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f72c516-3ad7-4c04-8ece-4ef59bbc362f · outbound

This paper cites Flowar: Scale-wise autoregressive image generation meets flow matching.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Flowar: Scale-wise autoregressive image generation meets flow matching

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:15.477595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 94c821a4-de10-4790-81ad-2d7123d4bd17 · outbound

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

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers High-resolution image synthesis with latent diffusion models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.277092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6398b433-bfa5-4f43-8e83-f8eeeefeec59 · outbound

This paper cites Progressive distillation for fast sampling of diffusion models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Progressive distillation for fast sampling of diffusion models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:15.272853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 321737fb-993e-48a6-a12b-32fbfd077602 · outbound

This paper cites Post-training quantization on diffusion models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Post-training quantization on diffusion models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:15.032194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c24fecb9-67b7-4ab2-a03d-d5e391791211 · outbound

This paper cites Deeply Supervised Flow-Based Generative Models.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Deeply Supervised Flow-Based Generative Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.513331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19ff55c3-075f-45ca-bbf3-7053f4ce474c · outbound

This paper cites Score-Based Generative Modeling through Stochastic Differential Equations.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Score-Based Generative Modeling through Stochastic Differential Equations

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.607502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ab29220-e2f7-49e4-a5c8-71683cfec651 · outbound

This paper cites Attention is all you need.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Attention is all you need

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.705712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a5d231c-f14c-4c32-ad4f-523e11f1d95d · outbound

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

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Wan: Open and Advanced Large-Scale Video Generative Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.772789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335f927a-0a5c-4a67-a57f-1cefeef14486 · outbound

This paper cites Axial- deeplab: Stand-alone axial-attention for panoptic segmentation.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Axial- deeplab: Stand-alone axial-attention for panoptic segmentation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:14.822785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 38e89115-e881-4974-8c2e-638c6bcb5b66 · outbound

This paper cites Linformer: Self-Attention with Linear Complexity.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Linformer: Self-Attention with Linear Complexity

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.991320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26888ff7-48f0-4f2b-a890-68aa6548ffe5 · outbound

This paper cites PPT: Token Pruning and Pooling for Efficient Vision Transformers.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers PPT: Token Pruning and Pooling for Efficient Vision Transformers

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.123223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d171f7b-9679-4dd8-98b7-0f4657292cc7 · outbound

This paper cites Revealing the dark secrets of masked image modeling.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Revealing the dark secrets of masked image modeling

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:14.625332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 21e1b526-6c24-4eb8-9732-6fa63313b9fa · outbound

This paper cites Imagereward: Learning and evaluating human preferences for text-to-image generation.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Imagereward: Learning and evaluating human preferences for text-to-image generation

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:14.439072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 20031a9d-1774-46c2-9f24-63e9b5f8b4bd · outbound

This paper cites 1.58-bit FLUX.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers 1.58-bit FLUX

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.353042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca922d8-374f-4f87-84ea-6bbce513e84b · outbound

This paper cites Randomized Autoregressive Visual Generation.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Randomized Autoregressive Visual Generation

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.464495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7620ea40-4ef0-47f6-b852-c29001f5d12e · outbound

This paper cites An image is worth 32 tokens for reconstruction and generation.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers An image is worth 32 tokens for reconstruction and generation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:14.221647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 57186a5d-b8a1-4890-9d3e-67454e39df8b · outbound

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

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Ditfastattn: Attention compression for diffusion transformer models

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:14.001466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 09a73369-39d8-4ca8-9def-216df835b5ed · outbound

This paper cites Big bird: Transformers for longer sequences.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Big bird: Transformers for longer sequences

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:13.837906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5f1ba8ba-8080-4e44-b3d1-2a3d53862c32 · outbound

This paper cites Fast Video Generation with Sliding Tile Attention.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers Fast Video Generation with Sliding Tile Attention

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.833852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e35993a9-d991-427b-84a6-22aa4778c62d · inbound

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking cites this paper.

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T15:10:05.851830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 43ca65b5-c884-476c-89eb-9a67ba031992 · inbound

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens cites this paper.

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:10:50.174151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b86c1ea3-1ce8-4a08-a0f2-0ad7cacd5cdf · inbound

Frequency-Aware Flow Matching for High-Quality Image Generation cites this paper.

Frequency-Aware Flow Matching for High-Quality Image Generation Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:00:04.105673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a1252ef0-c61f-4411-b75a-250093626758 · inbound

Efficient Video Diffusion Models: Advancements and Challenges cites this paper.

Efficient Video Diffusion Models: Advancements and Challenges Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 110

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:03:25.769904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 46388b3a-5e1a-407a-8fa7-2421d098f3b5 · inbound

Attention Sinks in Diffusion Transformers: A Causal Analysis cites this paper.

Attention Sinks in Diffusion Transformers: A Causal Analysis Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:24.044397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a5fff18d-56e4-433c-a0a9-601a2ebc0192 · inbound

Attention Sinks in Diffusion Transformers: A Causal Analysis cites this paper.

Attention Sinks in Diffusion Transformers: A Causal Analysis Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.283147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5a6911fb-01fb-4563-a1ba-bcbc644f8972 · inbound

Attention Sinks in Diffusion Transformers: A Causal Analysis cites this paper.

Attention Sinks in Diffusion Transformers: A Causal Analysis Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:45:46.111412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 03ed245a-a299-4c3a-9bee-234a7289ec20 · inbound

ACID: Adaptive Caching for vIDeo generation cites this paper.

ACID: Adaptive Caching for vIDeo generation Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T06:40:16.892454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.