Paper Citation Record · LEDGER

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization

As of 21 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2504.14534.

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

pith.paper-citation-record.v1
2504.14534 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:49:17.836268Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T15:33:30.182150Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T16:17:08.893198Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy13
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bedb5f25-8b30-4b8c-9efd-72604fc4661b · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Constitutional AI: Harmlessness from AI Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.691851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d31038ad-834b-43eb-b703-febd17a498fa · outbound

This paper cites Improving image generation with better captions.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Improving image generation with better captions

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.696683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b20899e1-48bb-43b5-aa58-070af1403e98 · outbound

This paper cites Training Diffusion Models with Reinforcement Learning.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Training Diffusion Models with Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.700298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 246fe53b-4057-4289-8486-ffdd4e61f49f · outbound

This paper cites Rank analysis of incomplete block designs: I.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Rank analysis of incomplete block designs: I

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.704537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ee8baa3-cf67-4f76-87cf-3225f2daa3c4 · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.707990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8110c9af-5564-4e70-81a6-9f307e21745a · outbound

This paper cites A simple framework for contrastive learning of visual representations.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization A simple framework for contrastive learning of visual representations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.711609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4db91052-95c3-490e-9ae0-ab81c91df7ac · outbound

This paper cites Directly Fine-Tuning Diffusion Models on Differentiable Rewards.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Directly Fine-Tuning Diffusion Models on Differentiable Rewards

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.714948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72777574-9efd-4b56-9607-c61123d309de · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.718896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 256549e1-8840-47aa-9f16-9c62118e0eed · outbound

This paper cites Diffusion models beat gans on image synthesis.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Diffusion models beat gans on image synthesis

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.722677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba98dd4e-f648-48fb-85f0-0baf940824cc · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.726094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3298e6c-85c2-4b41-800e-919aba529e65 · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.254965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d66e9b05-f61a-4667-af02-7c26c7cf411f · outbound

This paper cites Re- inforcement learning for fine-tuning text-to-image diffusion models.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Re- inforcement learning for fine-tuning text-to-image diffusion models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.244729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 350e9082-44e1-453f-b98d-821169662491 · outbound

This paper cites Generative adversarial nets.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Generative adversarial nets

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.736484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8278d76-6217-4c5d-9086-4993f5407753 · outbound

This paper cites Optimizing prompts for text-to-image generation.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Optimizing prompts for text-to-image generation

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.227551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fa584a57-cffb-445e-8901-9fe000d8cf57 · outbound

This paper cites Momentum contrast for unsupervised visual rep- resentation learning.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Momentum contrast for unsupervised visual rep- resentation learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.742653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10950062-8500-4826-b737-fb9e9cbeb35a · outbound

This paper cites Masked autoencoders are scalable vision learners.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Masked autoencoders are scalable vision learners

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.745634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eb58a61-844f-4cbb-902d-31dcfa1c9044 · outbound

This paper cites Denoising dif- fusion probabilistic models.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Denoising dif- fusion probabilistic models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.748614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dad04c7-0881-4041-954c-6d48aa26ce9d · outbound

This paper cites Auto-encoding vari- ational bayes, 2013.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Auto-encoding vari- ational bayes, 2013

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.751639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaed7431-8fac-4d18-9af8-180138ef45c6 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Pick-a-pic: An open dataset of user preferences for text-to-image generation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.189421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 21faa188-ecdf-4e11-97ab-e4a14da736a2 · outbound

This paper cites Flux, 2024.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Flux, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.178401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 131a6738-2a61-4947-afd5-d07ebf712d75 · outbound

This paper cites Aligning Text-to-Image Models using Human Feedback.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Aligning Text-to-Image Models using Human Feedback

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.760836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e411cb4-8bac-4caa-984f-7b58682d7061 · outbound

This paper cites Aligning diffusion mod- els by optimizing human utility.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Aligning diffusion mod- els by optimizing human utility

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.167684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 19f56009-acaa-4905-9dd4-7fb6034a54fe · outbound

This paper cites Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.767084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6d0f2d1-98cd-4ad7-b7f0-2763708c1625 · outbound

This paper cites Decoupled Weight Decay Regularization.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Decoupled Weight Decay Regularization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.770355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77cbd6de-d074-4b37-9bd1-294658eef2c5 · outbound

This paper cites GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.773564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2150bb7-ff5a-43e1-b56b-a1ec606eeea4 · outbound

This paper cites Training language models to follow instructions with human feedback.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Training language models to follow instructions with human feedback

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.776867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b54a22e-64ca-461d-80a7-47101da596c4 · outbound

This paper cites Scalable diffusion models with transformers.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Scalable diffusion models with transformers

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.780529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381f9b8e-8f54-47a1-bbef-71b50887efd3 · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.783907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36b221cd-f462-4a37-9940-6598570a4054 · outbound

This paper cites Aligning text-to-image diffusion models with reward backpropagation.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Aligning text-to-image diffusion models with reward backpropagation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.142745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation da1bc8e8-d953-458f-aa04-ff02a54aa51f · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Learning transferable visual models from natural language supervi- sion

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.790402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc108c0-a933-49db-ba13-2bf2cb94f691 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Direct preference optimization: Your language model is secretly a reward model

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.124051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8118be9d-8d55-4b5b-8a5a-064ba076fc3c · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization High-resolution image synthesis with latent diffusion models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.112520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c80de105-ce5c-4d73-b2bb-a6333b94bc24 · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Photorealistic text-to-image diffusion models with deep language understanding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.800413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb87d6fb-a8d3-4045-8acf-52d28988c944 · outbound

This paper cites Laion-aesthetics.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Laion-aesthetics

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.093835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1b2e92e8-4826-41f4-8c9f-177263c72d96 · outbound

This paper cites Adafactor: Adaptive learning rates with sublinear memory cost.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Adafactor: Adaptive learning rates with sublinear memory cost

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.806615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d214a64-4d5a-41d5-a86c-0740fa9ea7cb · outbound

This paper cites Neural discrete representation learning.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Neural discrete representation learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.810026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c46571-7a16-4e2b-9dc6-c3a19a4e6526 · outbound

This paper cites Diffusion model align- ment using direct preference optimization.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Diffusion model align- ment using direct preference optimization

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.067545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1a72071d-5138-43d7-ada9-b7c87d1eafbb · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.816031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f6bcd4b-e963-4f7c-8442-3b3dfd725670 · outbound

This paper cites SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.819446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adeb5111-c4a8-41ef-84b5-35b298151291 · outbound

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

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Imagere- ward: Learning and evaluating human preferences for text- to-image generation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.823108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdddc589-eaeb-4cf2-9a0c-3b49097d8173 · outbound

This paper cites Using human feedback to fine-tune diffusion models without any reward model.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Using human feedback to fine-tune diffusion models without any reward model

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.048655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a76e917d-1a40-4532-a85b-547aa287b871 · outbound

This paper cites Scaling Autoregressive Models for Content-Rich Text-to-Image Generation.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.829127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 977e2350-9bf4-495d-8114-12e24167279a · outbound

This paper cites Self-play fine-tuning of diffusion models for text-to-image generation.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Self-play fine-tuning of diffusion models for text-to-image generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T11:49:17.832595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43f506d-ed5a-47e8-9186-337d8dd4c5f4 · outbound

This paper cites Dspo: Direct score preference optimization for diffusion model alignment.

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization Dspo: Direct score preference optimization for diffusion model alignment

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:49:18.027836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 4ed4080b-a214-47bd-8b81-fd68de43048b · inbound

Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition cites this paper.

Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T22:16:16.544113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 99142947-ccbf-4b5b-8010-40c559cb63eb · inbound

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO cites this paper.

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:17:08.894690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.