Pith. sign in

Paper Citation Record · LEDGER

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

As of 9 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 2 inbound Pith citation observations for arXiv:2506.02221.

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

pith.paper-citation-record.v1
2506.02221 v1

Coverage vector

measured 68 of 68 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:34:06.057829Z

measured 70 of 70 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T05:35:48.896721Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T10:25:41.145492Z

Reference resolution

68 of 68 outbound references displayed

  • verified exact0
  • verified fuzzy37
  • unresolved31
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4c884881-ca4a-4c4a-b7a2-c16487079f9f · outbound

This paper cites Stochastic Interpolants: A Unifying Framework for Flows and Diffusions.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:57.630120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:57.630120Z digest=sha256:559484cf8b8543b3b0650471985dbf71f7a21b0c55f2e4ff4bfc0166e624954b

Observation 09f73fc6-c10a-408d-96ee-5763796ad1a5 · outbound

This paper cites Lora learns less and forgets less.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Lora learns less and forgets less

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:15.593051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:57.723681Z digest=sha256:a6756593f73fab6070008ebf5b24ad506c4bb2a11b34b7c129dc7765f1db9cf5

Observation c6bfefd8-8e32-4699-b119-e06682f1ac7e · outbound

This paper cites Align your latents: High-resolution video synthesis with la- tent diffusion models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Align your latents: High-resolution video synthesis with la- tent diffusion models

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:15.325378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:57.893588Z digest=sha256:ebb54551455af0df76e0ac90416314d91b0b1975442d9bde37804f88563a9211

Observation 24483d94-5ec4-48be-afe0-e669d2009361 · outbound

This paper cites Vir- tual kitti 2, 2020.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Vir- tual kitti 2, 2020

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:15.027331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:58.018451Z digest=sha256:c1e199fabb0f0b06148105dd72f6c512c92c3e4d313fc21e4e3c6f74056a4fb4

Observation ffc2993e-3895-4bdd-b35f-6aa6d17f41e3 · outbound

This paper cites Chang, Manolis Savva, Maciej Hal- ber, Thomas Funkhouser, and Matthias Nießner.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Chang, Manolis Savva, Maciej Hal- ber, Thomas Funkhouser, and Matthias Nießner

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:14.793462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:58.155108Z digest=sha256:e89c40282a3d7e159cd968d883ac82c0dd3672beb6543164adf3804ff4968845

Observation 3893c0ab-624b-4fb3-9fa7-6c360ff1166d · outbound

This paper cites Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:58.280467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:58.280467Z digest=sha256:2a5db1a920ca7a8691b8c111437a15cb8b7259d17a8cd35fa8336e6ccad1afba

Observation ed575bf2-ea23-4aaa-b78b-9c3f66bfe943 · outbound

This paper cites Generative Models: What Do They Know? Do They Know Things? Let's Find Out!.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Generative Models: What Do They Know? Do They Know Things? Let's Find Out!

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:58.437845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:58.437845Z digest=sha256:445a9d21b8b837fbc20f8a5362508e75d0754c492bec69579194464417fe0544

Observation 06706ecd-5d37-42f6-ac4a-c63adb71ee98 · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:14.520352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:58.567457Z digest=sha256:b88c8a6a397ba07e4cbed75e17fbf51b9fd69d0663cc4b78e99c4f2c4706796a

Observation 90a15785-eee4-4375-baf7-1765d3c82d9d · outbound

This paper cites Geowiz- ard: Unleashing the diffusion priors for 3d geometry estima- tion from a single image.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Geowiz- ard: Unleashing the diffusion priors for 3d geometry estima- tion from a single image

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:14.228704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:58.656501Z digest=sha256:a0b7ea92bda445c667b3d6192df7eda5ed00adc26acb23afab6a7f75de012f81

Observation 0d733709-b4b8-4a50-8da9-47e6f88a046f · outbound

This paper cites Diffusion Models and Representation Learning: A Survey.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Diffusion Models and Representation Learning: A Survey

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:58.810974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:58.810974Z digest=sha256:9c3b96c870819448168e09b4fd4ca23dcfe024db08d404ecfacf2173b9261644

Observation 566b0b82-812c-4702-b9b3-746829ef90fe · outbound

This paper cites Distillation of diffusion features for semantic correspondence.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Distillation of diffusion features for semantic correspondence

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:13.998848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:58.966709Z digest=sha256:dd4712c012362532626a834a8d7b2c1c0948d19656ff4928a897386bea55e1d5

Observation 041b8f47-16d5-4425-8dfc-5107e5f5f772 · outbound

This paper cites Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:59.076521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:59.076521Z digest=sha256:6325bafa8d4453d6efb45458047250cfa720e86489ba65aed23321cedf2b9572

Observation 955ad597-ed1a-4109-99d3-a508a3e85145 · outbound

This paper cites Vision meets robotics: The kitti dataset.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Vision meets robotics: The kitti dataset

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:59.188884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:59.188884Z digest=sha256:5f69c50398e309b579d22a95d5b75f803a32bf3c8613126159802e35157d5292

Observation ef40478a-da26-4d50-8a52-055132e27f34 · outbound

This paper cites Depthfm: Fast monocular depth estimation with flow matching.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Depthfm: Fast monocular depth estimation with flow matching

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:13.713098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:59.323082Z digest=sha256:31f5a934e43d978796354bd4839c0d0b7cbbe35ef8d7106ef26f6b4dde9229be

Observation 46b866d4-f5a1-4184-9df7-2f40c0b3dfda · outbound

This paper cites Animatediff: Animate your personalized text-to- image diffusion models without specific tuning.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Animatediff: Animate your personalized text-to- image diffusion models without specific tuning

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:59.397096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:59.397096Z digest=sha256:7eac4ee2feac31988e05b3ec58fcc4546c7e6a4c30360e39565c5569e137bdd2

Observation 30127671-5022-4262-aebe-6db07d384c1d · outbound

This paper cites Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T11:33:59.540350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:33:59.540350Z digest=sha256:d69cd3324ad6b650e0dda756a7959768a388e6d7569de4937155d004da1cd24b

Observation 055273bd-b2c2-4752-967b-2ccf86bf6c2a · outbound

This paper cites Scalecrafter: Tuning-free higher- resolution visual generation with diffusion models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Scalecrafter: Tuning-free higher- resolution visual generation with diffusion models

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:13.499803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:59.658359Z digest=sha256:ca0def1ef9ba7762fe7fe4651ce4ef1e5779eae0fc4d18b61131bf1c867eb09d

Observation 14b2b457-1036-49ed-9538-63bbf83bb551 · outbound

This paper cites Classifier-free diffusion guidance.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Classifier-free diffusion guidance

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:13.166177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:59.796870Z digest=sha256:d050aed3bd3b3170854c3a5d9467069275c57c1c5a8e19c8a9d0954a05bf983c

Observation ce8f5b7a-f7fa-4d9c-a7d4-fa17f89f0648 · outbound

This paper cites Denoising dif- fusion probabilistic models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Denoising dif- fusion probabilistic models

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:12.913159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:33:59.960055Z digest=sha256:580e5cf2bdb3fe9f11a29d8faee3136772063e75f878d60488e09e9cbfc83065

Observation 4467fa8f-e1d0-4cfc-8eb9-b720e18bd923 · outbound

This paper cites Video dif- fusion models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Video dif- fusion models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:00.071018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:00.071018Z digest=sha256:230f1f1f3b884eadf6ad2367f04610f0e2040ae82d4c627c0af0ed4b26126720

Observation 63699cd7-05c4-4f73-b785-43fcb7be7244 · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment LoRA: Low-rank adaptation of large language models

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:12.657054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:00.194593Z digest=sha256:06efbd5ab498a5bc2c1ba5b2c2000e3c0c1b2493e0a4e28d299798bec53fdfe1

Observation e47a2a94-5b3d-4d74-91c0-f467b6acf5ab · outbound

This paper cites Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:00.312873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:00.312873Z digest=sha256:dcfc233c01d3f3d917176dda8b571bc106cca2e737d1ca935e3827f758a54ad6

Observation 5b262491-79a5-4f11-ba1b-6e9472945dda · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Elucidating the design space of diffusion-based generative models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:00.433847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:00.433847Z digest=sha256:d98f4859932313402374f80b30e42c9722122615f3ea18c8f11b8a0b498d7a8e

Observation 5a8188f3-3090-4a80-88c1-2d695987005c · outbound

This paper cites Repurpos- ing diffusion-based image generators for monocular depth estimation.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Repurpos- ing diffusion-based image generators for monocular depth estimation

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:12.374917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:00.580884Z digest=sha256:05db8758f2a22a3767e746fcc4e93d8c502764d633954354402ab99dc013ce2b

Observation c6df2a8a-af85-4e11-b4dc-c271c82d854d · outbound

This paper cites Understanding diffu- sion objectives as the elbo with simple data augmentation.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Understanding diffu- sion objectives as the elbo with simple data augmentation

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:12.092308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:00.715793Z digest=sha256:41a5119f27738601f6be94eaff78a37b96e605733e727e428e84e11cef9fa4b8

Observation 182072cb-a137-437d-b425-98584247c792 · outbound

This paper cites an unresolved cited work.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Unresolved cited work

Reference 26

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:34:11.860273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:00.816159Z digest=sha256:b7398a7abf644ec89b20ea9cde7f3fb03b0a4a06b553aabe5f9fb67f14ba129f

Observation 69fb86f0-a302-4e5e-b21d-1aabb7b03387 · outbound

This paper cites Improving the training of rectified flows.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Improving the training of rectified flows

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:11.559543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:00.944316Z digest=sha256:dd1dd5c2b1c1a2dfb1a00c4eb6e454a89dfe6da0416fed71206f9497d3e23f26

Observation 1133d6c4-0cbd-40e3-9519-60684f9a1341 · outbound

This paper cites Common diffusion noise schedules and sample steps are flawed.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Common diffusion noise schedules and sample steps are flawed

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:11.300820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:01.071040Z digest=sha256:02782822ad19dbd0fb8446aea6d558647c9914fa5e1e7cd10b7bf41954509df2

Observation 0fd5534e-50c3-4f34-9280-8a73e6223725 · outbound

This paper cites Microsoft coco: Common objects in context.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Microsoft coco: Common objects in context

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:11.004246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:01.233435Z digest=sha256:9d18fc19104f9936f3b004e9e5e5b823528ae503d9e2865dbd5625f52b6d68ba

Observation 93703b74-7ac5-495d-9005-3311b3a5f20f · outbound

This paper cites Flow Matching for Generative Modeling.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Flow Matching for Generative Modeling

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:01.376255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:01.376255Z digest=sha256:4bcc240bbe60b3710424eb17b8537efcebd2ac13c140fc61227ec925b51d0de2

Observation 4c52cdeb-7932-49ff-b4ef-ac7ff4676e34 · outbound

This paper cites Au- dioldm: Text-to-audio generation with latent diffusion mod- els.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Au- dioldm: Text-to-audio generation with latent diffusion mod- els

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:10.764958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:01.508657Z digest=sha256:a22f6aac27c5b4062d65d307518490110a3fea8f42dc8f6ae25ea92ff4ea7086

Observation a9288bda-7f85-4e5b-b272-501676b62165 · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:01.622130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:01.622130Z digest=sha256:ec5a6262e58050f00dd45fc2b86bd88eedd062ffdf0900c36b0d6e411df7bfa1

Observation 42803282-daac-4045-a954-5a33b89917bd · outbound

This paper cites Instaflow: One step is enough for high-quality diffusion- based text-to-image generation.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Instaflow: One step is enough for high-quality diffusion- based text-to-image generation

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:01.753289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:01.753289Z digest=sha256:a5dff9377737741c02073d5532ed6d311d2f917a112809ae138fc4f018894c93

Observation f7a3e0c4-e90e-4652-9153-5ffbb70139f4 · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:01.865671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:01.865671Z digest=sha256:9bdced251e6d49bd42b395e6f99cf854417daa6cb920079b11ae427cff39e0cd

Observation 31fa962c-2337-41e2-aac2-1fd287387479 · outbound

This paper cites Diffusion hyperfeatures: searching through time and space for semantic correspondence.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Diffusion hyperfeatures: searching through time and space for semantic correspondence

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:10.527746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:01.968388Z digest=sha256:d526ae1bad5be570cb3cc52e8bb119e6b36370fa05ce578c92e36814486a2b04

Observation 5bc9a9ad-6133-478f-8300-e7f51e93a804 · outbound

This paper cites LCM-LoRA: A Universal Stable-Diffusion Acceleration Module.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:02.106675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:02.106675Z digest=sha256:5810e998408bb033f08dce3dcac829c8a7b23b6ff5dcd59207d7795c0494d5e9

Observation fd4c6d52-7a06-46d3-a29b-333bc1ac5793 · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:02.216529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:02.216529Z digest=sha256:5b1e6c8aaf5a57238e425add8d0f9338aa0a07e354ef4020add6dc548250fb49

Observation 3054d0a8-5d02-4817-9ca8-474fe10b2f04 · outbound

This paper cites Fine-tuning image-conditional diffusion models is easier than you think.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Fine-tuning image-conditional diffusion models is easier than you think

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:10.327087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:02.359009Z digest=sha256:5155b19384c84aa4a26a2d39c9331722bcffe9484d26cb78f512c7d8e9735750

Observation 52679af6-5c98-470a-9d41-1985177411e3 · outbound

This paper cites On distillation of guided diffusion models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment On distillation of guided diffusion models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:02.489052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:02.489052Z digest=sha256:616fa398dffcbc11c347fd18802055abfb99048339f470b87e106da7239167ba

Observation 96d4537b-f846-417d-a521-aa3a9a2ab92b · outbound

This paper cites Indoor segmentation and support inference from rgbd images.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Indoor segmentation and support inference from rgbd images

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:10.105627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:02.618331Z digest=sha256:01a823dffc0730378ef94b05748e78ec42a0e7224642a0beff2b38f2dfc3b613

Observation 61e2bea4-75f7-41e0-9d24-1dcff0759871 · outbound

This paper cites Glide: Towards photorealis- tic image generation and editing with text-guided diffusion models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Glide: Towards photorealis- tic image generation and editing with text-guided diffusion models

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:09.946784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:02.766180Z digest=sha256:28563372904d423193fc18649417c947ac89ec1ad57353b32aaec4f249b19368

Observation fb33c966-5050-48a6-b74e-4b48f4d2980a · outbound

This paper cites Scalable diffusion models with transformers.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Scalable diffusion models with transformers

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:02.883059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:02.883059Z digest=sha256:943bdb87460d0f219105c06744ef5607566a2fb029cbddbd40476c65ce3c14de

Observation 010479a1-0213-4a40-956c-5c9dc29de2ac · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Sdxl: Improving latent diffusion models for high-resolution image synthesis

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:09.720622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:02.988081Z digest=sha256:d6b2971d4325626e2ef8a74700ee3d0e6ca8acd54e10c8266ce2fca58a43e2eb

Observation 0b59607d-31c9-4f0d-9ad9-918f9dd02bc9 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:03.095241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:03.095241Z digest=sha256:07382934fd31012052b93ef4ac89933fd9901afd1aca8f9a70ce89b7fdefa10a

Observation f5365c08-cfd2-49ef-90d9-e1c90a50ba8c · outbound

This paper cites Susskind.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Susskind

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:03.195615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:03.195615Z digest=sha256:33d9d62aefe236bb381e0c3c38788398589cc36751800daef2882e90f775eaee

Observation a22a4fbb-72a8-4617-abdd-543f4221ccad · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment High-resolution image synthesis with latent diffusion models

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:09.453738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:03.322025Z digest=sha256:f4251944235690961ecf875fe19825c6e15163b9623992c15edac9038869d436

Observation d245481c-2358-4167-87af-d99d4ad24d66 · outbound

This paper cites Low-rank adaptation for fast text- to-image diffusion fine-tuning.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Low-rank adaptation for fast text- to-image diffusion fine-tuning

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:09.234129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:03.471645Z digest=sha256:4deddddb7315e5e990659e7b4c3b5ca0ade554fa079a94494bb0d4cb0a722dd2

Observation dde4719c-5170-4d7b-a41c-f0c684e5051b · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Photorealistic text-to-image diffusion models with deep language understanding

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:09.027062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:03.584269Z digest=sha256:9d743152ccac1f587d3ca4b7f4028126cd9ba0cdf9414f17807c96454d8f441c

Observation cead7f1f-7032-477e-b3c8-9ae3e366852b · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Progressive distillation for fast sampling of diffusion models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:03.667772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:03.667772Z digest=sha256:e78afcb9f27a2be43e0ed20d8aaa101eb6752511f6ed095f23ddac45d3e961bf

Observation e51e8f78-9113-4390-9b9b-37b51c542c3a · outbound

This paper cites Adversarial diffusion distillation.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Adversarial diffusion distillation

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:03.788564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:03.788564Z digest=sha256:d6afff4807ac4981270851ad9260b94e898dae2a82a582e976d95274145275bf

Observation f62b748c-a7e3-4957-b59b-14089bf70a18 · outbound

This paper cites Monocular Depth Estimation using Diffusion Models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Monocular Depth Estimation using Diffusion Models

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:03.910640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:03.910640Z digest=sha256:b49c743f1bf2c82768f95d83f75f20b306b3e9070f9dfa5f5c5498cf58660978

Observation 3292057f-e716-4294-874b-a0e052c37ba0 · outbound

This paper cites A multi-view stereo benchmark with high- resolution images and multi-camera videos.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment A multi-view stereo benchmark with high- resolution images and multi-camera videos

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:08.798622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:04.035802Z digest=sha256:31d6ed9763bb254bc8c9f59aa61df98fd5a24d2134be6e10adcbaf2932147150

Observation a5c544ad-6120-4e69-b739-1cd475547ba1 · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:08.529539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:04.190227Z digest=sha256:2fe468858a5e8f74e8f75e28d7fd7d579871f31ff17a561859f367d56b5e913e

Observation 2d1c8ad0-5bb5-4bf6-bfa0-dab3aaee1a71 · outbound

This paper cites Boosting latent diffusion with flow match- ing.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Boosting latent diffusion with flow match- ing

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:08.340180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:04.279419Z digest=sha256:e8921bf6b2e5910bd448bf772739f44efd457f5499ce9bff43dd90a1471a2a4e

Observation d9779b2e-53c0-4f18-8bd2-14a708ad5230 · outbound

This paper cites Bespoke Solvers for Generative Flow Models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Bespoke Solvers for Generative Flow Models

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:04.386658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:04.386658Z digest=sha256:5e8cd546c7594e61ba698a2cefca498b548fef158a8f6abcbebe24588157e447

Observation c3332ee6-5cb1-4f4a-a2ae-5ac67bb8d792 · outbound

This paper cites Denois- ing diffusion implicit models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Denois- ing diffusion implicit models

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:04.521602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:04.521602Z digest=sha256:ebb646595f56c2f8a7aa36a8047b1a188387dbb49c9a0590b9f98fcbf56827f0

Observation 2a658d97-a691-42cb-9d4d-6987d014a980 · outbound

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

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Score-Based Generative Modeling through Stochastic Differential Equations

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:04.679153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:04.679153Z digest=sha256:c23116561d78c0c811c488480dbad1fc73a300d975ac3d2d7f84afa2dd331ffd

Observation 73550a7a-9b08-4887-9ac7-bf600b94e075 · outbound

This paper cites Consistency models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Consistency models

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:08.099595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:04.795451Z digest=sha256:b88b6c12cc1d4e998f23c6424de3d6b9d8e830bb149061c2640d092f07c41180

Observation cdedb216-4f22-4e79-9202-ef095ca9fd34 · outbound

This paper cites CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:04.864808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:04.864808Z digest=sha256:d5c525210b3fc90193204153a6de69aa21d962bbd8f839f6efa5b94cee94bd48

Observation ad02aebd-de39-40dc-9a9d-33b3408882a3 · outbound

This paper cites Emergent correspondence from im- age diffusion.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Emergent correspondence from im- age diffusion

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:07.842580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:04.983292Z digest=sha256:135d0d02eafbdbcb2886f33a6267ca12686374b7ac5c91442c803988218f975f

Observation 4642e35f-dad1-4c71-918e-c92347fa758c · outbound

This paper cites Improving and generalizing flow-based gen- erative models with minibatch optimal transport.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Improving and generalizing flow-based gen- erative models with minibatch optimal transport

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:07.620005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:05.092925Z digest=sha256:0ebad619fd16780230141c105f20fd7a84986b2f40444f77ef0f060f18102dae

Observation 14ac07bd-4129-4399-aa56-68c8f75bc536 · outbound

This paper cites Dai, Andrea F.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Dai, Andrea F

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:07.365097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:05.190794Z digest=sha256:8c594646776023cebc1d1d7067a2c11991ac8e285cc609de19fc9841ec8016c3

Observation 6d58f621-00be-4cbb-847b-87f84cacab1c · outbound

This paper cites Open-vocabulary panop- tic segmentation with text-to-image diffusion models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Open-vocabulary panop- tic segmentation with text-to-image diffusion models

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:07.126883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:05.357414Z digest=sha256:98c519b6fc72e28a096a4a2e15a53676ba4dc71fe9225f85bb82b8a0f59566fb

Observation 09d023ca-7e5a-4dc7-9541-028ff014344b · outbound

This paper cites Perflow: Piecewise rectified flow as universal plug-and-play accelerator, 2024.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Perflow: Piecewise rectified flow as universal plug-and-play accelerator, 2024

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:06.921645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:05.474230Z digest=sha256:9a2e341c2ba513ce2b8ee8c33caa566b0119aee5b77a104cecc97c3cb2f56a69

Observation da54b21e-18f7-4472-ac26-439596bd0d4b · outbound

This paper cites Depth anything: Unleashing the power of large-scale unlabeled data.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Depth anything: Unleashing the power of large-scale unlabeled data

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:06.717559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:05.623240Z digest=sha256:9450678dea8c8858e2cd6e934f17e2cedef757673c4eb407f1174b185f2a12a5

Observation 74412f08-06d0-4ffd-a2a3-b61b6aca16ac · outbound

This paper cites Depth Anything V2.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment Depth Anything V2

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:05.787660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:05.787660Z digest=sha256:5ed2432d142d4f4969ba2fc4526a8a03a8ad013e9dec82e33fe41c0b6b16d8da

Observation 87d761b5-1a3d-47cf-8cc1-f9181fbca22e · outbound

This paper cites IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-07T11:34:05.953733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:34:05.953733Z digest=sha256:443968f0bfbf6ed86e1b1d8ef0d6dcde724040e73d854214e7584ab1e6897dc2

Observation 0a61bb08-d273-4344-87e2-5971c583c968 · outbound

This paper cites LoRA base.

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment LoRA base

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:34:06.486250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T11:34:06.057829Z digest=sha256:b35b88f2169fcbd8c41d970d0884b1918978baa0d15e54b1f6b5bde7b57c8033

Pith citing papers

Observation f0180740-5d93-476b-8863-53d1152ef251 · inbound

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling cites this paper.

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

Reference 69

Resolution
verified exact
arxiv_id, observed 2026-05-12T10:16:28.982692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-07T06:38:04.459129Z digest=sha256:c03b28ad639bbc0f05cd0ffe16435783ffe323e60d6f84a7e139248ad9bfbe53

Observation dd3f2424-bdf2-40b5-b989-5e8586110d37 · inbound

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers cites this paper.

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

Reference 43

Resolution
verified exact
arxiv_id, observed 2026-07-01T10:25:41.147057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-07-01T05:35:48.896721Z digest=sha256:b16802fa11751b84eb00d1430efd44071ca44ee5cc7bafd549c46fe3b1847212