Paper Citation Record · LEDGER

Towards Self-Improvement of Diffusion Models via Group Preference Optimization

As of 18 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 3 inbound Pith citation observations for arXiv:2505.11070.

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

pith.paper-citation-record.v1
2505.11070 v1

Coverage vector

measured 71 of 71 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:03:31.022584Z

measured 74 of 74 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-15T01:22:42.691009Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T01:23:26.825361Z

Reference resolution

71 of 71 outbound references displayed

verified exact0
verified fuzzy13
unresolved58
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0e953848-7065-4f72-ada8-c6169d4c3a71 · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.102049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7847d3a9-e927-45de-a57d-1f04bb30df03 · outbound

This paper cites A Noise is Worth Diffusion Guidance.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization A Noise is Worth Diffusion Guidance

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.108005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b758ff8-c5b1-43df-a53c-5c8df4595df2 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.170314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274f9632-d4b2-4cbe-97ea-3eca80d4da9d · outbound

This paper cites Improving image generation with better captions.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Improving image generation with better captions

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.316991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13f56677-9437-4626-9d64-409c9deda726 · outbound

This paper cites Make It Count: Text-to-Image Generation with an Accurate Number of Objects.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Make It Count: Text-to-Image Generation with an Accurate Number of Objects

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.329115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b09b675c-fb17-4f90-aa27-2c290cb92c9b · outbound

This paper cites Training diffusion models with reinforcement learning.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Training diffusion models with reinforcement learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.995342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ee70a06d-53a8-4807-8b65-3af4aff2b3cd · outbound

This paper cites Text-to-image diffusion models cannot count, and prompt refinement cannot help.arXiv preprint arXiv:2503.06884, 2025.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Text-to-image diffusion models cannot count, and prompt refinement cannot help.arXiv preprint arXiv:2503.06884, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.476120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cebc991-728a-4b46-9925-428d474a7f4d · outbound

This paper cites Getting it right: Improving spatial consistency in text-to-image models.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Getting it right: Improving spatial consistency in text-to-image models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.523559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85053dad-5263-49cc-a503-64ffad5c5e10 · outbound

This paper cites Textdiffuser: Diffusion models as text painters.Advances in Neural Information Processing Systems, 36: 9353–9387, 2023.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Textdiffuser: Diffusion models as text painters.Advances in Neural Information Processing Systems, 36: 9353–9387, 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.527769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 490fc261-c788-4740-81df-2631e3e86dca · outbound

This paper cites Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30, 2017.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30, 2017

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.532979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7974a9e4-7d50-4056-b250-d96f0e658b5b · outbound

This paper cites Directly fine-tuning diffusion models on differentiable rewards.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Directly fine-tuning diffusion models on differentiable rewards

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.828398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fd9813fa-7e29-4c47-b405-ff5940ae63aa · outbound

This paper cites Less is more: Improving llm alignment via preference data selection.arXiv preprint arXiv:2502.14560, 2025.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Less is more: Improving llm alignment via preference data selection.arXiv preprint arXiv:2502.14560, 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.657047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 802229b2-2d11-4950-90a3-c2a389ac29fd · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Scaling rectified flow trans- formers for high-resolution image synthesis

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.682007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e94ab5b-e4bd-4edb-be33-6c4e400249d9 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization KTO: Model Alignment as Prospect Theoretic Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.687518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf19877-b93a-433e-9dc7-06259cc06206 · outbound

This paper cites Denoising diffusion probabilistic models.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Denoising diffusion probabilistic models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.804017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3933286f-f058-40f8-a72c-4d45250068da · outbound

This paper cites Reference-free monolithic preference optimization with odds ratio.arXiv e-prints, pages arXiv–2403, 2024.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Reference-free monolithic preference optimization with odds ratio.arXiv e-prints, pages arXiv–2403, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.697525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 00fd11c1-05f9-4d37-b7ef-a67ee53eacd0 · outbound

This paper cites ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.788600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6648fcc-ffa9-4c7e-8497-f112840fc5cb · outbound

This paper cites T2i-compbench: A compre- hensive benchmark for open-world compositional text-to-image generation.Advances in Neural Information Processing Systems, 36:78723–78747, 2023.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization T2i-compbench: A compre- hensive benchmark for open-world compositional text-to-image generation.Advances in Neural Information Processing Systems, 36:78723–78747, 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.831361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99bf66c8-fe77-45bc-b392-8f90721ccfea · outbound

This paper cites Ultralytics YOLO, 2023.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Ultralytics YOLO, 2023

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.673547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fa1324b2-863e-477f-ab83-6a35503a4b45 · outbound

This paper cites Scalable Ranked Preference Optimization for Text-to-Image Generation.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Scalable Ranked Preference Optimization for Text-to-Image Generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.841117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41ef1a48-bd0c-432d-9b17-adaa98cef521 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.Advances in Neural Information Processing Systems, 36:36652–36663, 2023.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Pick-a-pic: An open dataset of user preferences for text-to-image generation.Advances in Neural Information Processing Systems, 36:36652–36663, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.845960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 753bfbe8-e6be-47c9-8903-f0ad461da02b · outbound

This paper cites Flux.https://github.com/black-forest-labs/flux, 2024.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Flux.https://github.com/black-forest-labs/flux, 2024

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.869669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a828dea-16ed-4a1a-848b-d20c5775bb74 · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Aligning Text-to-Image Models using Human Feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:29.937680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51015cd7-63b9-4238-8436-75b259f13879 · outbound

This paper cites Calibrated multi-preference optimization for aligning diffusion models.arXiv preprint arXiv:2502.02588, 2025.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Calibrated multi-preference optimization for aligning diffusion models.arXiv preprint arXiv:2502.02588, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.002767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4ee8f8d-cac5-4bfd-a506-c99538d45ba6 · outbound

This paper cites Align- ing diffusion models by optimizing human utility.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Align- ing diffusion models by optimizing human utility

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.338641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 692af499-7b68-439b-b86f-5f343ccd17bd · outbound

This paper cites Policy Optimization in RLHF: The Impact of Out-of-preference Data.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Policy Optimization in RLHF: The Impact of Out-of-preference Data

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.012249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb14da43-0d95-488c-9015-fa9e59c6b20a · outbound

This paper cites Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.017303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 129297b4-09fd-40ea-a54c-ae81a42d30ca · outbound

This paper cites Flow matching for generative modeling.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Flow matching for generative modeling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.106144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347b89c1-dce8-4a8c-b6bd-4879a2c168b5 · outbound

This paper cites Alignment of diffusion models: Fundamentals, challenges, and future.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Alignment of diffusion models: Fundamentals, challenges, and future

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.142072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad9a4394-030f-4035-8356-659cde4c78f7 · outbound

This paper cites Character-Aware Models Improve Visual Text Rendering.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Character-Aware Models Improve Visual Text Rendering

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.147094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7355a2d9-b7e8-42e2-91fd-ff64e0913867 · outbound

This paper cites VideoDPO: Omni-Preference Alignment for Video Diffusion Generation.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization VideoDPO: Omni-Preference Alignment for Video Diffusion Generation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.152272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f1472b5-1879-433b-a93f-c5ea1d7bd393 · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Flow straight and fast: Learning to generate and transfer data with rectified flow

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.191853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c6ac3c-ca9d-42eb-b226-cdc85e0e8b1b · outbound

This paper cites Decoupled Weight Decay Regularization.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Decoupled Weight Decay Regularization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.282842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48a563b7-d952-4734-8505-5712db092a4c · outbound

This paper cites Exploring the role of large language models in prompt encoding for diffusion models.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Exploring the role of large language models in prompt encoding for diffusion models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.179537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 17db391e-f2af-416f-b3ca-a10e8e8a9c16 · outbound

This paper cites Simpo: Simple preference optimization with a reference-free reward.Advances in Neural Information Processing Systems, 37:124198–124235, 2024.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Simpo: Simple preference optimization with a reference-free reward.Advances in Neural Information Processing Systems, 37:124198–124235, 2024

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.313409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6089de64-5d4e-41ce-83e3-739a35e9b911 · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Sdxl: Improving latent diffusion models for high-resolution image synthesis

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.318162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5058c826-aea0-4f94-9d09-1cee8912daf0 · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Direct preference optimization: Your language model is secretly a reward model

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.322997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd28208b-e9c4-42b2-b0aa-2e5254280c9e · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization High- resolution image synthesis with latent diffusion models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.366530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a72b7d1-e6df-4507-a3cf-eeb20fc67e37 · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.446989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45d2b281-0a38-48fa-99fa-5ccfd26354f2 · outbound

This paper cites Laion- 5b: An open large-scale dataset for training next generation image-text models.Advances in neural information processing systems, 35:25278–25294, 2022.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Laion- 5b: An open large-scale dataset for training next generation image-text models.Advances in neural information processing systems, 35:25278–25294, 2022

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.485008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6823a61-d656-4790-8d6c-9655808ba213 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Proximal Policy Optimization Algorithms

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.489775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d89ee5c9-9d03-4f0d-90ac-c25e60b3c2d4 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.494204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e736897-9f34-4cb9-bfd4-96b931107ada · outbound

This paper cites Anytext: Multilingual visual text generation and editing.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Anytext: Multilingual visual text generation and editing

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:33.022200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3a6b9c14-9c8b-455d-b7f5-01fb6c82dd8c · outbound

This paper cites Diffusion model alignment using direct preference optimization.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Diffusion model alignment using direct preference optimization

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.503325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cb75f59-a21e-4fa2-9456-d42ff7802ef0 · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Wan: Open and Advanced Large-Scale Video Generative Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.507321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf9200d-ece3-44ff-b486-f4709ca2e5f3 · outbound

This paper cites The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.511812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f14d9f-2060-4f2c-8819-a6aa77223df2 · outbound

This paper cites DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.516736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3664726c-4fec-46f3-837d-d7a6c116194f · outbound

This paper cites Human preference score: Better aligning text-to-image models with human preference.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Human preference score: Better aligning text-to-image models with human preference

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.567176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 369312ab-7a59-462a-8f81-bc13e6d06e98 · outbound

This paper cites Deep reward supervisions for tuning text-to-image diffusion models.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Deep reward supervisions for tuning text-to-image diffusion models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:32.870282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f38f5e4-7a63-41a5-bca5-9f0599f5fecd · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Imagereward: Learning and evaluating human preferences for text-to-image generation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.722215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21e201c2-65be-41fe-8724-13950d14673c · outbound

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

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Using human feedback to fine-tune diffusion models without any reward model

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.772282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10b0b9e1-be8f-45db-ae76-2ea878cc25c6 · outbound

This paper cites Adding conditional control to text-to-image diffusion models.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Adding conditional control to text-to-image diffusion models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.811452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7861898-c017-4067-bb12-1a43efed4515 · outbound

This paper cites Learning multi-dimensional human preference for text-to-image generation.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Learning multi-dimensional human preference for text-to-image generation

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.816995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69be1f60-03dd-406b-b8ec-019c665d638d · outbound

This paper cites Diffusion model as a noise-aware latent reward model for step-level preference optimization.arXiv preprint arXiv:2502.01051, 2025.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Diffusion model as a noise-aware latent reward model for step-level preference optimization.arXiv preprint arXiv:2502.01051, 2025

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.820896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc874733-eb87-47e4-b933-973e3c9ca48f · outbound

This paper cites Cogview3: Finer and faster text-to-image generation via relay diffusion.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Cogview3: Finer and faster text-to-image generation via relay diffusion

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:32.752256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 95c13eee-ed9d-4de1-a004-14e332433c13 · outbound

This paper cites Golden Noise for Diffusion Models: A Learning Framework.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Golden Noise for Diffusion Models: A Learning Framework

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:30.829602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c98595b-93a2-4b0e-9e5b-33e3db25fbe5 · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.548329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 64ab745c-29ef-4a14-85cb-0f4cd9dfd25f · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.534768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fe7e4b3a-0210-4be2-97b5-eca49a76c89d · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.389993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d07bf9d1-835b-4e23-97b1-aa17533e6cad · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.376602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1433c578-539f-46ad-b25b-ae04574bf9f6 · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.289980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b771aa8f-e089-4911-85f6-55c2d7047938 · outbound

This paper cites [Example Template] Input: 3 cat Output: Three cats curled up together on a sunny windowsill.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization [Example Template] Input: 3 cat Output: Three cats curled up together on a sunny windowsill

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:32.146541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cfc0a1e3-6450-4c63-af16-b93324284294 · outbound

This paper cites Follow these guidelines: [Output Requirements] Generate prompts with this structure:.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Follow these guidelines: [Output Requirements] Generate prompts with this structure:

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:32.070189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8795ca4e-7c45-45c4-ba0f-35930758bef0 · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.054519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 03d3efa6-e140-40c1-824d-4639cd532fb1 · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.362009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 546442cd-8ab0-4243-b532-2b14d0d3ccef · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.038270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ed76670d-67ac-44f9-adf9-a9a1398d391c · outbound

This paper cites [Optimization Principles].

Towards Self-Improvement of Diffusion Models via Group Preference Optimization [Optimization Principles]

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:03:31.810325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3f7af134-3d70-4f97-a6fe-0c11e796209c · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.114769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e389d7ff-09e1-44da-8ef1-406603d085b6 · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.100930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0606f03b-ce42-4e69-8271-8dae054c9e40 · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:32.085862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 025ed2ad-7697-43b0-b4d3-de71033cffcd · outbound

This paper cites an unresolved cited work.

Towards Self-Improvement of Diffusion Models via Group Preference Optimization Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:03:31.771090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 6cbf8414-1296-427e-8e31-d67b50a322cd · inbound

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal cites this paper.

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal Towards Self-Improvement of Diffusion Models via Group Preference Optimization

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-15T01:23:26.827986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d933ab5c-a43a-49a1-a136-38b95e3dbd6c · inbound

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling cites this paper.

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling Towards Self-Improvement of Diffusion Models via Group Preference Optimization

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:21:07.642353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3cf3dc95-2919-4c21-b3b7-80f0b4092774 · inbound

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories cites this paper.

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories Towards Self-Improvement of Diffusion Models via Group Preference Optimization

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:25:18.862887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.