Paper Citation Record · LEDGER

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

As of 3 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 1 inbound Pith citation observation for arXiv:2604.25477.

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

pith.paper-citation-record.v1
2604.25477 v1

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-07T16:44:23.162726Z

measured 64 of 64 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T12:46:26.361155Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

63 of 63 outbound references displayed

verified exact40
verified fuzzy23
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 73740e02-0d96-42af-b0d1-c863b672fd23 · outbound

This paper cites Qwen-image technical report.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Qwen-image technical report

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.760044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation da4a5169-94a5-481b-8ab0-f078f695bc58 · outbound

This paper cites Flux.1: Text-to-image synthesis via flow matching.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Flux.1: Text-to-image synthesis via flow matching

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.773716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e6407dff-9705-4b86-afee-73f05f1833de · outbound

This paper cites LongCat-Image Technical Report.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing LongCat-Image Technical Report

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:04:13.097348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cf2b0ef5-1e57-459e-b41a-f72aca7847a8 · outbound

This paper cites Diffusion Models Beat GANs on Image Synthesis.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Diffusion Models Beat GANs on Image Synthesis

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-13T11:16:28.664120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 29e42942-a3e1-4ebd-8478-6575cafff5a9 · outbound

This paper cites Diffusion model alignment using direct preference optimization.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Diffusion model alignment using direct preference optimization

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.770111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9f34a434-2d96-44b6-ab1d-403f338e664d · outbound

This paper cites Diffusion model-based image editing: A survey.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Diffusion model-based image editing: A survey

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.752553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cabc0059-27d7-411b-9ee9-83a62f687b16 · outbound

This paper cites Available: https://doi.org/10.1109/TPAMI.2025.3541625.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Available: https://doi.org/10.1109/TPAMI.2025.3541625

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.528913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f72f2bd4-68eb-4927-84df-9deef36d0aba · outbound

This paper cites Freeedit: Mask-free reference-based image editing with multi-modal instruction.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Freeedit: Mask-free reference-based image editing with multi-modal instruction

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.337125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ad58f7de-10e7-4ba9-8171-728d7b61b5c1 · outbound

This paper cites Instructpix2pix: Learning to follow image editing instructions.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Instructpix2pix: Learning to follow image editing instructions

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.725917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation bb741fb7-3229-4ecf-a488-0edd62e06dc6 · outbound

This paper cites Opencir: Conditional image repainting with open condition mixture.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Opencir: Conditional image repainting with open condition mixture

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.440860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9a8624f9-312b-4bea-a374-182e61e83d85 · outbound

This paper cites Step1X-Edit: A Practical Framework for General Image Editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Step1X-Edit: A Practical Framework for General Image Editing

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:36:15.161347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 828ea5b4-6b90-4c8a-a609-701280c1e461 · outbound

This paper cites ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.891845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3736c31e-088e-43c5-9a0d-6b294d69ec5a · outbound

This paper cites T2i- compbench++: An enhanced and comprehensive benchmark for compositional text-to-image generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing T2i- compbench++: An enhanced and comprehensive benchmark for compositional text-to-image generation

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.360355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3afb7641-7d3e-4996-8de2-cc175bde9563 · outbound

This paper cites LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.439069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 04fc640f-7be7-417c-995c-3be27584dd79 · outbound

This paper cites Editthinker: Unlocking iterative reasoning for any image editor.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Editthinker: Unlocking iterative reasoning for any image editor

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.742542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 16a7fbc1-2d8c-48ad-8c84-ba5171ba6826 · outbound

This paper cites Spatialreward: Verifiable spatial re- ward modeling for fine-grained spatial consistency in text-to- image generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Spatialreward: Verifiable spatial re- ward modeling for fine-grained spatial consistency in text-to- image generation

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.468761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 899c43b0-7284-45d5-8a66-1a0a484e91e6 · outbound

This paper cites Evaluating compositional text-to-image generation: A benchmark and analysis.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Evaluating compositional text-to-image generation: A benchmark and analysis

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.732948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b303e3d6-e2f8-47f2-ac89-4f9147c95d6b · outbound

This paper cites Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.352173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 27ecd09a-cb02-4b5f-8f12-068f456b3d98 · outbound

This paper cites Unified Thinker: A General Reasoning Modular Core for Image Generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Unified Thinker: A General Reasoning Modular Core for Image Generation

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:36:14.310359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation fc5f3209-64c3-4ef7-ae61-48c2e210d57c · outbound

This paper cites ThinkRL-Edit: Thinking in reinforcement learning for reasoning-centric image editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing ThinkRL-Edit: Thinking in reinforcement learning for reasoning-centric image editing

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.406277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 11f8678b-52ee-46bb-a237-a2a095868069 · outbound

This paper cites Thinkgen: Generalized thinking for visual generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Thinkgen: Generalized thinking for visual generation

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.616239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0b79ee05-19de-4b75-9059-95910782387a · outbound

This paper cites Reasonedit: Towards reasoning-enhanced image editing models.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Reasonedit: Towards reasoning-enhanced image editing models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.710775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b3c75896-eef1-4f10-a2cf-0c9328b07adc · outbound

This paper cites Flow-GRPO: Training Flow Matching Models via Online RL.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Flow-GRPO: Training Flow Matching Models via Online RL

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:36:14.265384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c25d9c85-cabc-4024-a324-d784b274e793 · outbound

This paper cites DanceGRPO: Unleashing GRPO on Visual Generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing DanceGRPO: Unleashing GRPO on Visual Generation

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:36:14.547536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 64613d6a-9da2-4229-81cf-77bb937a4c28 · outbound

This paper cites Text-guided human image manipulation via image-text shared space.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Text-guided human image manipulation via image-text shared space

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.476823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6a5a6188-b894-4023-9c52-5bf9bb7e0c77 · outbound

This paper cites Consistent image layout editing with diffusion models.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Consistent image layout editing with diffusion models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.729744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b1e52f75-d346-4692-ae33-8a7dc5409961 · outbound

This paper cites Instruction-driven multi-weather image translation based on a large-scale image editing model.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Instruction-driven multi-weather image translation based on a large-scale image editing model

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.777501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation df5b1cae-7ac9-4b93-85a4-596b0a45b8ec · outbound

This paper cites Spherical patch generative adversarial net for unconditional panoramic image generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Spherical patch generative adversarial net for unconditional panoramic image generation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.766814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e2488ebd-e723-465e-a624-17eb706f3741 · outbound

This paper cites Talk-to-edit: Fine-grained 2d and 3d facial editing via dialog.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Talk-to-edit: Fine-grained 2d and 3d facial editing via dialog

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.540347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c55d235e-5357-4cbf-b99f-4d7a887201ad · outbound

This paper cites Pixel-inconsistency modeling for image manipulation localization.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Pixel-inconsistency modeling for image manipulation localization

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.703325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1c32b0bc-f36b-4399-bb2c-308a63bd4c8c · outbound

This paper cites Available: https://doi.org/10.1109/TPAMI.2025.3541028.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Available: https://doi.org/10.1109/TPAMI.2025.3541028

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.324518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6b8c1c3e-7906-4516-854c-c5d66461ae70 · outbound

This paper cites DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.501643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d8a0129d-69c8-44e9-8535-45921df8aa5c · outbound

This paper cites Unit: Unified multimodal chain-of-thought test-time scaling.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Unit: Unified multimodal chain-of-thought test-time scaling

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.991572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation fcd9db07-65e3-46c4-ad55-35d2c64da4f8 · outbound

This paper cites EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-06-19T17:11:33.200899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b8c0d12c-b40a-44b2-b485-9237c2a35a49 · outbound

This paper cites Promptrl: Prompt matters in rl for flow-based image generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Promptrl: Prompt matters in rl for flow-based image generation

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.423005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5069e3b1-03fb-4cd7-ac4c-5045a2fe31c9 · outbound

This paper cites Consensus- agent deep reinforcement learning for face aging.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Consensus- agent deep reinforcement learning for face aging

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.505730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 867a5b1b-9c61-49c5-b085-af5d8f4e8a46 · outbound

This paper cites RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-17T02:20:37.504540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3013bbfc-e023-45e3-bcf8-905ad6be7cf9 · outbound

This paper cites Unireason 1.0: A unified reasoning framework for world knowledge aligned image generation and editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Unireason 1.0: A unified reasoning framework for world knowledge aligned image generation and editing

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.295984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a554675a-cfa5-4429-b558-f0de6edad0a5 · outbound

This paper cites Think-then-generate: Reasoning-aware text-to-image diffusion with llm encoders.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Think-then-generate: Reasoning-aware text-to-image diffusion with llm encoders

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.509617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e21c94ba-54da-47bc-b5b6-1dc291e982b4 · outbound

This paper cites Edit-r1: Unleashing reasoning-based reinforcement learning for image editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Edit-r1: Unleashing reasoning-based reinforcement learning for image editing

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.714241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 60500e0a-e98e-4cdb-bab1-659564550e67 · outbound

This paper cites WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-15T16:24:27.819650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9cb1fd09-c8e8-422d-a062-c3282912cde1 · outbound

This paper cites Spatialclip: Learning 3d-aware image representations from spatially discriminative language.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Spatialclip: Learning 3d-aware image representations from spatially discriminative language

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.739413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation dd654700-f1a2-4a2c-8b0c-cde4dba1cc01 · outbound

This paper cites OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.767670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b31ef99a-4856-4ea1-9156-853034934313 · outbound

This paper cites Describe, spot and explain: Interpretable representation learning for discriminative visual reasoning.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Describe, spot and explain: Interpretable representation learning for discriminative visual reasoning

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-09T01:54:33.518102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 70a50361-b532-424a-bf54-9d9835b922f9 · outbound

This paper cites Editscore: Unlocking online rl for image editing via high-fidelity reward modeling.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Editscore: Unlocking online rl for image editing via high-fidelity reward modeling

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.389149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3868c4d7-7de3-46c5-9218-3dfcd9f085f1 · outbound

This paper cites Editreward: A human- aligned reward model for instruction-guided image editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Editreward: A human- aligned reward model for instruction-guided image editing

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.458415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e9f2bb27-9ede-4220-9e40-7ad7c4d29650 · outbound

This paper cites Decompose and compare consistency: Measuring vlms’ answer reliability via task-decomposition consistency comparison.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Decompose and compare consistency: Measuring vlms’ answer reliability via task-decomposition consistency comparison

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.717723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8cc3be6f-688a-4af2-a6da-c2c03df58f84 · outbound

This paper cites A minimalist approach to llm reasoning: from rejection sampling to reinforce.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing A minimalist approach to llm reasoning: from rejection sampling to reinforce

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.745853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 13fbd3b2-276d-40d2-a930-0b52616a2d80 · outbound

This paper cites Star-ds: Step-level uncertainty-aware reasoning data selection in reinforcement learning for llm multi-step reasoning.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Star-ds: Step-level uncertainty-aware reasoning data selection in reinforcement learning for llm multi-step reasoning

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.706888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ba05cc04-9a67-48db-bad7-3ebdac4a083f · outbound

This paper cites Deepseekmath: Pushing the limits of mathematical reasoning in open language models.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Deepseekmath: Pushing the limits of mathematical reasoning in open language models

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.721277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation df859c47-4841-44d5-bc39-21db35dd212c · outbound

This paper cites Generative multimodal models are in-context learners.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Generative multimodal models are in-context learners

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.735789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e2e9b417-bf7c-4baa-88d4-7b6fc997eee4 · outbound

This paper cites Omnigen: Unified image generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Omnigen: Unified image generation

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.749137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a6b4084a-6e5c-4be7-b4d8-b60f0d7ccc78 · outbound

This paper cites Ovis: Structural Embedding Alignment for Multimodal Large Language Model.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Ovis: Structural Embedding Alignment for Multimodal Large Language Model

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.874224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6aca301e-b303-4904-b415-24b450a7d9eb · outbound

This paper cites Emerging Properties in Unified Multimodal Pretraining.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Emerging Properties in Unified Multimodal Pretraining

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:36:14.448393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation af292168-a3a3-45c9-870e-4093f538a5f4 · outbound

This paper cites Uni-cot: Towards unified chain-of-thought reasoning across text and vision.arXiv preprint arXiv:2508.05606.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Uni-cot: Towards unified chain-of-thought reasoning across text and vision.arXiv preprint arXiv:2508.05606

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation fbbc63a1-53f6-4066-b9cd-f6e3dd5593ea · outbound

This paper cites Magicbrush: A manually annotated dataset for instruction-guided image editing.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Magicbrush: A manually annotated dataset for instruction-guided image editing

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.756741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a4a839c6-1044-4bb1-a390-b194736c4edc · outbound

This paper cites Anyedit: Mastering unified high-quality image editing for any idea.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Anyedit: Mastering unified high-quality image editing for any idea

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.763254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 555a3239-68b4-41bd-8c0e-c1a7bc3856e1 · outbound

This paper cites HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:13:39.137651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cc3ba391-0e60-4e04-8d7c-82b41e592fad · outbound

This paper cites ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.376218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ee52f3b7-b9ad-4781-99ba-833876aff080 · outbound

This paper cites OmniGen2: Towards Instruction-Aligned Multimodal Generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing OmniGen2: Towards Instruction-Aligned Multimodal Generation

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:36:15.095575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 903d680e-eb14-4211-995c-f28a796fab80 · outbound

This paper cites UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-12T17:34:27.304691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3cd9d8c5-c127-464c-8674-8b05fbce0139 · outbound

This paper cites Qwen3-vl technical report.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Qwen3-vl technical report

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-27T01:53:22.781074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 985954a5-013f-4361-bb59-b5aa280e606d · outbound

This paper cites KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models.

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:36:14.561125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Pith citing papers

Observation 7986f710-a863-4c66-abf6-9f4786b1f9fa · inbound

ExpertVerse: A General-Purpose Benchmark for Expert-Level Reasoning in Knowledge-Intensive Visual Synthesis cites this paper.

ExpertVerse: A General-Purpose Benchmark for Expert-Level Reasoning in Knowledge-Intensive Visual Synthesis DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T12:46:26.361155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.