Paper Citation Record · LEDGER

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

As of 23 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 1 inbound Pith citation observation for arXiv:2412.16822.

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

pith.paper-citation-record.v1
2412.16822 v2

Coverage vector

measured 60 of 60 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T10:19:29.941556Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-15T15:10:00.146694Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T15:10:05.816056Z

Reference resolution

60 of 60 outbound references displayed

verified exact1
verified fuzzy24
unresolved33
parse uncertain1
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ebbc3e73-5ed1-4838-b804-c21660e94ee2 · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers All are worth words: A vit backbone for diffusion models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.525018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d81689af-b793-481a-81f9-affc20d295ca · outbound

This paper cites Token merging for fast sta- ble diffusion.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Token merging for fast sta- ble diffusion

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.723755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0a1168b-6d85-4d2c-bfd6-c2cdcd66bbb3 · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.728288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8be5aada-a0be-43f3-9c43-c27a89fc7fcc · outbound

This paper cites PixArt-\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers PixArt-\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.732653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79de1df7-647a-40cb-9785-91e1dade57a0 · outbound

This paper cites Diffrate: Differentiable compression rate for efficient vision transformers.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Diffrate: Differentiable compression rate for efficient vision transformers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.504845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 912cf782-2953-4b88-9eed-801d39e0114a · outbound

This paper cites Model compression and hardware acceleration for neural networks: A comprehensive survey.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Model compression and hardware acceleration for neural networks: A comprehensive survey

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.493082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98f017d1-6969-46e2-b503-325b2ea7f70f · outbound

This paper cites Diffusion models beat gans on image synthesis.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Diffusion models beat gans on image synthesis

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.743859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a17822d-3b8a-47ae-8b9b-8121d578c557 · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.474145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bda2a9a4-0727-496c-8665-68b5cebb1393 · outbound

This paper cites Structural pruning for diffusion models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Structural pruning for diffusion models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.461308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b89da4e1-cee5-417d-860b-7992339cd277 · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.754665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d517559c-c93f-40f1-87bb-c8d967b9b0d1 · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Gans trained by a two time-scale update rule converge to a local nash equilib- rium

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.758610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eef887ff-19fc-43df-bd99-4a02a449a44c · outbound

This paper cites Classifier-Free Diffusion Guidance.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Classifier-Free Diffusion Guidance

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.762349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 785dfbd3-487a-4862-bb8f-b4083d97bf3b · outbound

This paper cites Denoising dif- fusion probabilistic models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Denoising dif- fusion probabilistic models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.766353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1be7ddc2-69bf-4a59-ae3d-b180ec2bff3e · outbound

This paper cites Multi-Scale Dense Networks for Resource Efficient Image Classification.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Multi-Scale Dense Networks for Resource Efficient Image Classification

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.769516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503cefdd-ef8a-47ec-82bc-a9f9056a12a6 · outbound

This paper cites Distilling diffusion models into condi- tional gans.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Distilling diffusion models into condi- tional gans

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.436031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6513af6d-518b-4b20-b72c-53ce87cd1222 · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Elucidating the design space of diffusion-based generative models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.777857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ccf4c35-c86d-45ff-b4cd-c8bd90eb9ccf · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.781983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 919043a1-1882-470a-b7e2-bc4a7650dbe2 · outbound

This paper cites Microsoft coco: Common objects in context.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Microsoft coco: Common objects in context

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.786396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 651f29b3-5412-4ec5-96bb-7ddd2343836d · outbound

This paper cites Faster Diffusion via Temporal Attention Decomposition.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Faster Diffusion via Temporal Attention Decomposition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.789872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ecfe594-ed7d-416d-8647-64f6732baa9a · outbound

This paper cites Decoupled weight decay regularization.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Decoupled weight decay regularization

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.412034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 429ed189-f1bb-4a08-86bd-274e50711012 · outbound

This paper cites Dpm-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Dpm-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.400426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 14dadf01-8d5f-4fb4-80df-21de457fa0bc · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.800222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77746eb2-aeed-4195-95b9-3b17f3aff3ef · outbound

This paper cites On distillation of guided diffusion models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers On distillation of guided diffusion models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.388750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation afd40078-6e9d-42f4-b8f7-ae00a8583baa · outbound

This paper cites Early exiting for acceler- ated inference in diffusion models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Early exiting for acceler- ated inference in diffusion models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.377069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 89e95efa-02aa-405b-a05e-0bd99a54944d · outbound

This paper cites Cache me if you can: Effects of dns time-to-live.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Cache me if you can: Effects of dns time-to-live

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.366364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b37b2d60-be7f-47ed-8d89-316571c9d115 · outbound

This paper cites Hydranets: Specialized dynamic archi- tectures for efficient inference.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Hydranets: Specialized dynamic archi- tectures for efficient inference

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.355313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation de4690be-6d13-4178-8fb2-0a69714f2467 · outbound

This paper cites Improved denoising diffusion probabilistic models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Improved denoising diffusion probabilistic models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.343434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0141d69a-1e41-496d-8c23-40bcddf4c890 · outbound

This paper cites Lazy Diffusion Transformer for Interactive Image Editing.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Lazy Diffusion Transformer for Interactive Image Editing

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.823420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0475ad0c-2e9f-482f-8d11-8ae19f1639e3 · outbound

This paper cites Scalable diffusion models with transformers.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Scalable diffusion models with transformers

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.827736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baf5a7fb-4163-4caf-9fcf-b08adecd0689 · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.831150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4094fbc-4424-45c6-8723-2deeeb0a507f · outbound

This paper cites Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-11T10:19:30.064145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 503e79ac-a328-42b2-9939-e323d17a8dcf · outbound

This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.837971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80d1bcf4-8648-45b6-8ae3-2ca5fe86240d · outbound

This paper cites Mixture-of-Depths: Dynamically allocating compute in transformer-based language models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.841358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 426bafbd-06fb-4ef7-9f50-3c9fd828bbd1 · outbound

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

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers High-resolution image synthesis with latent diffusion models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.844852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f5b23c-6a0b-43c1-ba03-c4255fa1a928 · outbound

This paper cites Progressive Distillation for Fast Sampling of Diffusion Models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Progressive Distillation for Fast Sampling of Diffusion Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.848351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e8c37ed-06fe-4b15-b98c-a8d3120f0fb2 · outbound

This paper cites Adversarial diffusion distillation.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Adversarial diffusion distillation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.851986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f168f87b-5e6e-421e-8616-36273c0f5ef0 · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.855718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c079068-dbd0-49e6-8284-3745a8c66e62 · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.309186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5efc1f43-ba81-40bc-9119-03f4b09125b7 · outbound

This paper cites ToDo: Token Downsampling for Efficient Generation of High-Resolution Images.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers ToDo: Token Downsampling for Efficient Generation of High-Resolution Images

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.862542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e366d5-df8a-4e78-9f4b-718e4d947ed6 · outbound

This paper cites Deep unsupervised learning using nonequilibrium thermodynamics.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Deep unsupervised learning using nonequilibrium thermodynamics

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.866320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16dda16c-ef06-4dd6-a760-08c771a4b285 · outbound

This paper cites Denoising Diffusion Implicit Models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Denoising Diffusion Implicit Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.869594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eeaa2e1-840e-45a2-a607-12bf8395dcbc · outbound

This paper cites Branchynet: Fast inference via early exiting from deep neural networks.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Branchynet: Fast inference via early exiting from deep neural networks

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.293300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 33a0fec6-cfec-44f5-b629-85a049999f81 · outbound

This paper cites Attention is all you need.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Attention is all you need

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.878058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc5eaee-be30-4723-8e06-491955fa4e90 · outbound

This paper cites Diffusers: State-of-the-art diffu- sion models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Diffusers: State-of-the-art diffu- sion models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.882004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 258589c3-0c16-411e-9bea-0624276416ca · outbound

This paper cites Attention-driven training-free efficiency enhancement of diffusion models.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Attention-driven training-free efficiency enhancement of diffusion models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.272389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 39c5fb13-4cc5-49ca-b3ca-ebc05602107d · outbound

This paper cites A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.888841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4fd9c29-eed4-4f99-99a8-a336f83aaba6 · outbound

This paper cites Imagen editor and editbench: Advancing and evaluating text-guided im- age inpainting.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Imagen editor and editbench: Advancing and evaluating text-guided im- age inpainting

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.262567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8f0edd99-33ad-49ac-97e2-4e291111d53e · outbound

This paper cites Skipnet: Learning dynamic routing in convolutional networks.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Skipnet: Learning dynamic routing in convolutional networks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.895782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6606519-f20d-434e-a6ba-e20cf580d6a5 · outbound

This paper cites Dual dynamic inference: Enabling more efficient, adap- tive, and controllable deep inference.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Dual dynamic inference: Enabling more efficient, adap- tive, and controllable deep inference

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.246935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fc802f1e-dfbd-4c5a-ad9f-43a8772be5b1 · outbound

This paper cites https : / / github.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers https : / / github

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.235632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5fcd236f-533d-404d-84c8-0adcf75831c1 · outbound

This paper cites Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.910760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa16123b-0b75-4507-be32-5169d40332da · outbound

This paper cites Blockdrop: Dynamic inference paths in residual networks.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Blockdrop: Dynamic inference paths in residual networks

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.214344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6dbdc0e0-f6fb-4c7f-af43-b15c3e28debe · outbound

This paper cites Smartbrush: Text and shape guided object inpainting with diffusion model.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Smartbrush: Text and shape guided object inpainting with diffusion model

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.203984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation df162457-6804-4737-a2b8-2195d6e0e9f8 · outbound

This paper cites Deepcache: Principled cache for mo- bile deep vision.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Deepcache: Principled cache for mo- bile deep vision

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.192917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 554d4e5d-7984-436b-87a9-38f39b3478ef · outbound

This paper cites Improved Distribution Matching Distillation for Fast Image Synthesis.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Improved Distribution Matching Distillation for Fast Image Synthesis

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.926869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d697ca8b-bee2-4c14-a7e9-eeaec51df75d · outbound

This paper cites One-step diffusion with distribution matching distillation.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers One-step diffusion with distribution matching distillation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.182657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 94277dbe-e238-40db-b542-465abc75524b · outbound

This paper cites Not all tokens are equal: Human-centric visual analysis via token clustering transformer.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Not all tokens are equal: Human-centric visual analysis via token clustering transformer

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:19:30.171362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d6418dc0-ac6f-41fe-aee6-a90e65478485 · outbound

This paper cites Dynamic Diffusion Transformer.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Dynamic Diffusion Transformer

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T10:19:29.937840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f11bed25-02f1-42a3-9d29-576d23ff5d8e · outbound

This paper cites an unresolved cited work.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers Unresolved cited work

Reference 2023

Resolution: parse uncertain; raw_fallback, observed 2026-08-11T10:19:30.225257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 65fb917c-416b-4800-8645-d7fafb70a69c · outbound

This paper cites eel sushi roll.

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers eel sushi roll

Reference 2024

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T10:19:30.161075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 416a6da0-af1f-4331-8737-fec204e8b8ed · 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 Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T15:10:05.819805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.