Paper Citation Record · LEDGER

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

As of 11 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 2 inbound Pith citation observations for arXiv:2603.12893.

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

pith.paper-citation-record.v1
2603.12893 v2

Coverage vector

measured 76 of 76 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-14T22:03:10.367971Z

measured 78 of 78 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T20:38:28.328436Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-03T04:17:36.942540Z

Reference resolution

76 of 76 outbound references displayed

verified exact0
verified fuzzy0
unresolved76
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation df89649d-d771-428e-9174-b4a7615e87af · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10093cc1-6f88-4656-8e0b-f1a2254d206f · outbound

This paper cites Albergo and Eric Vanden-Eijnden.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Albergo and Eric Vanden-Eijnden

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a773175-9372-4c7e-9f34-472adb41df24 · outbound

This paper cites Concrete Problems in AI Safety.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Concrete Problems in AI Safety

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e1f61f6-e5c6-424d-81c9-895c5f4f8aaf · outbound

This paper cites Ascher and Linda R.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Ascher and Linda R

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03215930-610a-412c-be0b-31527cd48692 · outbound

This paper cites Flow network based generative models for non-iterative diverse candidate generation.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Flow network based generative models for non-iterative diverse candidate generation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a817c6c-77e8-4225-8a6c-5fe12bf9f4a3 · outbound

This paper cites Training diffusion models with reinforcement learning.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Training diffusion models with reinforcement learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50a429a2-8fe6-4bb7-bb10-101651f78fb6 · outbound

This paper cites OneIG-Bench: Omni-dimensional nuanced evaluation for image generation.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models OneIG-Bench: Omni-dimensional nuanced evaluation for image generation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90ba2d62-a540-4d2a-a868-78a6b2e723e1 · outbound

This paper cites Chen, Yaron Vaxman, Elad Ben Baruch, David Asulin, Aviad Moreshet, Kuo-Chin Lien, Misha Sra, and Pradeep Sen.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Chen, Yaron Vaxman, Elad Ben Baruch, David Asulin, Aviad Moreshet, Kuo-Chin Lien, Misha Sra, and Pradeep Sen

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2afce917-308f-40e6-99c7-bef4973d110d · outbound

This paper cites ILVR: Conditioning method for denoising diffusion probabilistic models.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models ILVR: Conditioning method for denoising diffusion probabilistic models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a88fd9cf-5e26-4315-bab8-d254eb783a49 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03cec0de-d364-4b96-83da-ae48b7af36c6 · outbound

This paper cites Inversion by direct iteration: An alternative to denoising diffusion for image restoration.TMLR, 2023.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Inversion by direct iteration: An alternative to denoising diffusion for image restoration.TMLR, 2023

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e9f63d-fc62-4eed-8457-73eaa4dff997 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89d2936b-b7de-47a5-aded-b3ca594984c2 · outbound

This paper cites RAFT: Reward ranked finetuning for generative foundation model alignment.TMLR, 2023.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models RAFT: Reward ranked finetuning for generative foundation model alignment.TMLR, 2023

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d32ab0b-b5e2-4706-a120-39ddba554a0b · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Scaling rectified flow transformers for high-resolution image synthesis

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6db57836-1380-45eb-a399-10e51ad95142 · outbound

This paper cites Online reward-weighted fine-tuning of flow matching with Wasserstein regularization.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Online reward-weighted fine-tuning of flow matching with Wasserstein regularization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff162c4-2d2d-4536-972a-0f64651e2526 · outbound

This paper cites DPOK: Reinforcement learning for fine-tuning text-to-image diffu- sion models.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models DPOK: Reinforcement learning for fine-tuning text-to-image diffu- sion models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3595b3-afb1-4092-8b38-f5fe06160bb9 · outbound

This paper cites DreamSim: Learning new dimensions of human visual similarity using synthetic data.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models DreamSim: Learning new dimensions of human visual similarity using synthetic data

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96c2e77-9204-42db-9abe-c34bcd9d82aa · outbound

This paper cites Gradient guidance for diffusion models: An optimization perspective.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Gradient guidance for diffusion models: An optimization perspective

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97d210b8-c37a-420a-bba7-bc882ad59551 · outbound

This paper cites Iterative α-(de)blending: A minimalist deterministic diffusion model.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Iterative α-(de)blending: A minimalist deterministic diffusion model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f9ef5af-191c-4ece-b011-fc30f516b78d · outbound

This paper cites Classifier-free diffusion guid- ance.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Classifier-free diffusion guid- ance

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd7d01f8-a4ac-42b8-970a-d90ec6adab52 · outbound

This paper cites Denoising dif- fusion probabilistic models.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Denoising dif- fusion probabilistic models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a294e3fa-fbb2-4553-a981-1c932f55914f · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models LoRA: Low-rank adaptation of large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ddfbd59-f690-410a-b79e-bb098edf4e43 · outbound

This paper cites Reward fine-tuning two-step diffusion models via learning differentiable latent-space surrogate reward.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Reward fine-tuning two-step diffusion models via learning differentiable latent-space surrogate reward

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da4b4f96-2697-4c8d-b7e3-951277b878d3 · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Elucidating the design space of diffusion-based generative models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21b1c436-b7bd-4543-a490-7d28acb84083 · outbound

This paper cites Understanding DDPM latent codes through optimal transport.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Understanding DDPM latent codes through optimal transport

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbced906-46ab-4ee6-b137-19fe9346a5df · outbound

This paper cites Dif- fusionCLIP: Text-guided diffusion models for robust image manipulation.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Dif- fusionCLIP: Text-guided diffusion models for robust image manipulation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2edaf55d-7485-4660-8390-f5c24a3c2678 · outbound

This paper cites Pick-a-Pic: An open dataset of user preferences for text-to-image genera- tion.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Pick-a-Pic: An open dataset of user preferences for text-to-image genera- tion

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57bc139c-3a38-4f0c-a407-578414dc2e5a · outbound

This paper cites The flow map of the Fokker–Planck equation does not provide optimal trans- port.Appl.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models The flow map of the Fokker–Planck equation does not provide optimal trans- port.Appl

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea3083ad-3013-4409-861b-c868138c8dc2 · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Aligning Text-to-Image Models using Human Feedback

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fab0d1aa-bc9a-40fb-80f5-fe567e288a7a · outbound

This paper cites Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 890d1674-7098-4c24-8056-0e02add15924 · outbound

This paper cites Eval- uating text-to-visual generation with image-to-text generation.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Eval- uating text-to-visual generation with image-to-text generation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59c1d1de-1c30-458a-9448-b0f75d78b0e6 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a42c165-df84-4fa5-93cd-44e6b1028c5c · outbound

This paper cites Kwok, Sumi Helal, and Zeke Xie.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Kwok, Sumi Helal, and Zeke Xie

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de898c8e-2a76-4183-82ce-44a7eb7f8616 · outbound

This paper cites Flow-GRPO: Training flow matching models via online RL.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Flow-GRPO: Training flow matching models via online RL

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aa6bacb-5471-4c1a-a5f0-876d5c8a1cf3 · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Flow straight and fast: Learning to generate and transfer data with rectified flow

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 239459d1-3bbe-45ee-80de-363a02504997 · outbound

This paper cites Xiao, Weiyang Liu, Yoshua Bengio, and Dinghuai Zhang.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Xiao, Weiyang Liu, Yoshua Bengio, and Dinghuai Zhang

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62d93d67-9652-4a1e-bbaf-f13dd1a88ebb · outbound

This paper cites Decoupled weight decay regularization.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Decoupled weight decay regularization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac87837-35e0-4b97-aed7-454a0d323bbd · outbound

This paper cites Dual-process image generation.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Dual-process image generation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8da4d78-202d-4132-9495-cefd97ccfda6 · outbound

This paper cites Flow matching policy gradients.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Flow matching policy gradients

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96149dc8-9af5-4643-86c8-8296b1a229fb · outbound

This paper cites SDEdit: Guided image synthesis and editing with stochastic differential equations.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models SDEdit: Guided image synthesis and editing with stochastic differential equations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e51a865-7793-4b86-95ce-add2d17b269e · outbound

This paper cites Bridging the gap between value and policy based reinforcement learning.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Bridging the gap between value and policy based reinforcement learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 193a33bc-dbfc-42b0-92df-c49bd6753b13 · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models WebGPT: Browser-assisted question-answering with human feedback

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d178709-b4f8-44b7-a8ae-f357b89d32a2 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f1bf9a3-9c29-4db3-b812-6f27c009acc9 · outbound

This paper cites Flow Q- learning.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Flow Q- learning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c17c4f6-5759-484a-a772-3a62675a0bf3 · outbound

This paper cites Reinforcement learning by reward-weighted regression for operational space control.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Reinforcement learning by reward-weighted regression for operational space control

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9138516-452f-48a6-a758-1c4271c58a25 · outbound

This paper cites Learning a diffusion model policy from rewards via Q-score matching.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Learning a diffusion model policy from rewards via Q-score matching

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18f5b110-4262-48a7-af33-628028bcbd19 · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Learning transferable visual models from natural language supervision

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c524408-3fff-4c39-82b3-019da6536d9f · outbound

This paper cites co/openai/clip-vit-large-patch14.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models co/openai/clip-vit-large-patch14

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80dd83a1-60c5-4da8-9fba-7995d2bf2007 · outbound

This paper cites Manning, and Chelsea Finn.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Manning, and Chelsea Finn

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63ce22b6-ee54-452c-bd5b-c9b3d0fb5437 · outbound

This paper cites The cross-entropy method for combina- torial and continuous optimization.Method.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models The cross-entropy method for combina- torial and continuous optimization.Method

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba92b2e0-e54f-4902-b4db-2d01f14f4b42 · outbound

This paper cites Birkhäuser, 2015.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Birkhäuser, 2015

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94ada230-4a1e-486d-9a6f-b08fb04fe3fe · outbound

This paper cites Proximal Policy Optimization Algorithms.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Proximal Policy Optimization Algorithms

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3414cd60-74b5-4fc2-b153-9ec23321299e · outbound

This paper cites Deep unsupervised learning using nonequilibrium thermodynamics.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Deep unsupervised learning using nonequilibrium thermodynamics

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d1a233f-f761-44b8-ae84-f63cf433f5e6 · outbound

This paper cites Denoising diffusion implicit models.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Denoising diffusion implicit models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c3e5a40-7c0f-4e5d-a020-a946c7c69dca · outbound

This paper cites Loss-guided diffusion models for plug-and-play con- trollable generation.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Loss-guided diffusion models for plug-and-play con- trollable generation

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 765e5280-9f67-416f-93e0-0c60d3f1fa66 · outbound

This paper cites Generative modeling by estimating gradients of the data distribution.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Generative modeling by estimating gradients of the data distribution

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 100ca1cd-917f-4d5e-91ec-90156c440359 · outbound

This paper cites Kingma, Ab- hishek Kumar, Stefano Ermon, and Ben Poole.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Kingma, Ab- hishek Kumar, Stefano Ermon, and Ben Poole

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 193a9dbb-e70c-4103-a5f6-eb03ad00ab0e · outbound

This paper cites Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54caf120-9198-46fa-bdc5-308984419f4a · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Diffusion model align- ment using direct preference optimization

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b039da8c-f9fb-48e8-95d0-2231a6417c53 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cbba29c-164e-45f6-a308-65fed8b64b8e · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bac1c88-225d-44f8-a00e-e341ca045f45 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e8acc0d-a2c0-487f-9472-ea0c9e41e453 · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2c807b-d702-433f-be21-a1aa9de992e0 · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Deep reward supervisions for tuning text-to-image diffusion models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6bf4148-b02d-4fae-82e4-a3f939e85612 · outbound

This paper cites Simple policy optimization.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Simple policy optimization

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80da336e-ad3e-4fa7-83ea-21c16683d652 · outbound

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

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models ImageReward: Learning and evaluating human preferences for text-to-image generation

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f50656bf-e991-4def-a11b-8d59b1b6fb9c · outbound

This paper cites Advantage weighted matching: Aligning RL with pretraining in diffusion models.CoRR, abs/2509.25050,.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Advantage weighted matching: Aligning RL with pretraining in diffusion models.CoRR, abs/2509.25050,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d07fead-3202-40a1-98f1-d21c77790297 · outbound

This paper cites DanceGRPO: Unleashing GRPO on Visual Generation.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models DanceGRPO: Unleashing GRPO on Visual Generation

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4dee3f3-4c05-4f72-89f0-a42d5dabdfff · outbound

This paper cites Good- man.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Good- man

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27dd3634-e9d4-4b42-a15e-1f145997df34 · outbound

This paper cites Does this image match the caption.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Does this image match the caption

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeedd373-5203-434e-b11a-65a22e470d58 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3ebed2b-7982-486e-94e0-809426fdbe33 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f6a081-4af7-4710-8e94-06db6514ce52 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b04716c9-e8ce-47b8-869d-b62aa92dd355 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02abbdaa-7d45-49b6-a41d-16de4d56fe81 · outbound

This paper cites an unresolved cited work.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models Unresolved cited work

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88ed38df-319e-4d2c-a716-50a6ea6eb19c · outbound

This paper cites fleshed out.

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models fleshed out

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-14T22:03:10.367971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d6dc629b-76e2-4f3e-8aac-2d2a8f9f72cd · inbound

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO cites this paper.

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

Reference 89

Resolution: verified exact; local_arxiv, observed 2026-07-01T14:35:47.194282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1ab9285b-9fb1-48d0-8866-fc55328a2cd3 · inbound

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning cites this paper.

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-03T04:17:36.943719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.