mlsanityData to 7 Oct 2026

Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

arXiv 2504.02826 ↗First posted 3 Apr 2025cs.CVcited by 97

Not on the map. Why?

Cited by 27 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE). RISEBench focuses on four key reasoning categories: Temporal, Causal, Spatial, and Logical Reasoning. We curate high-quality test cases for each category and propose an robust evaluation framework that assesses Instruction Reasoning, Appearance Consistency, and Visual Plausibility with both human judges and the LMM-as-a-judge approach. We conducted experiments evaluating nine prominent visual editing models, comprising both open-source and proprietary models. The evaluation results demonstrate that current models face significant challenges in reasoning-based editing tasks. Even the most powerful model evaluated, GPT-4o-Image, achieves an accuracy of merely 28.8%. RISEBench effectively highlights the limitations of contemporary editing models, provides valuable insights, and indicates potential future directions for the field of reasoning-aware visual editing. Our code and data have been released at https://github.com/PhoenixZ810/RISEBench.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 3 Apr 2025.

Builds on

38 of 51 references.

References · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2024GPT-4o System Cardcited by 4,467
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  7. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  9. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  10. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  11. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  12. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
26 more
  1. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  2. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  3. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  4. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  5. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  6. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  7. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  8. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 468
  9. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  10. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  11. 2024OmniGen: Unified Image Generationcited by 388
  12. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 290
  13. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  14. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 284
  15. 2023Generating Images with Multimodal Language Modelscited by 259
  16. 2023T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generationcited by 253
  17. 2024LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contextscited by 240
  18. 2025WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generationcited by 196
  19. 2023HIVE: Harnessing Human Feedback for Instructional Visual Editingcited by 172
  20. 2024Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-trainingcited by 82
  21. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  22. 2025LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?cited by 49
  23. 2024SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Foldingcited by 42
  24. 2023VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generationcited by 41
  25. 2020Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructionscited by 25
  26. 2024PUMA: Empowering Unified MLLM with Multi-granular Visual Generationcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 29; 2026: 68.

97 papers.

Sort:

By area:

  1. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  2. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 193
  3. 2025On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectificationcited by 121
  4. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  5. 2025KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Modelscited by 69
  6. 2025Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Visioncited by 52
  7. 2025R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generationcited by 31
  8. 2025Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmarkcited by 28
  9. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 27
  10. 2025UniREditBench: A Unified Reasoning-based Image Editing Benchmarkcited by 23
  11. 2025EditThinker: Unlocking Iterative Reasoning for Any Image Editorcited by 23
  12. 2026UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervisioncited by 23
38 more
  1. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 23
  2. 2025GenExam: A Multidisciplinary Text-to-Image Examcited by 19
  3. 2026Visual Generation Unlocks Human-Like Reasoning through Multimodal World Modelscited by 18
  4. 2026Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generationcited by 18
  5. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 16
  6. 2025Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Imagecited by 16
  7. 2025GIR-Bench: Versatile Benchmark for Generating Images with Reasoningcited by 15
  8. 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoderscited by 15
  9. 2025ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generationcited by 14
  10. 2026DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editingcited by 14
  11. 2025PICABench: How Far Are We from Physically Realistic Image Editing?cited by 13
  12. 2025ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generationcited by 13
  13. 2025RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligencecited by 12
  14. 2025ThinkGen: Generalized Thinking for Visual Generationcited by 12
  15. 2026How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editingcited by 12
  16. 2025ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representationscited by 11
  17. 2026Quantifying the Gap between Understanding and Generation within Unified Multimodal Modelscited by 11
  18. 2026GENIUS: Generative Fluid Intelligence Evaluation Suitecited by 11
  19. 2025WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editingcited by 10
  20. 2026ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editingcited by 10
  21. 2026RISE-Video: Can Video Generators Decode Implicit World Rules?cited by 10
  22. 2025RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editingcited by 9
  23. 2026UEval: A Benchmark for Unified Multimodal Generationcited by 9
  24. 2026Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generationcited by 9
  25. 2025MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generationcited by 8
  26. 2026Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utilitycited by 8
  27. 2026Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generationcited by 8
  28. 2025R-Genie: Reasoning-Guided Generative Image Editingcited by 6
  29. 2025Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learningcited by 6
  30. 2026UReason: Benchmarking Reasoning-to-Generation Alignment in Unified Multimodal Modelscited by 6
  31. 2026WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editingcited by 6
  32. 2026Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modelingcited by 6
  33. 2026Unified Thinker: A General Reasoning Modular Core for Image Generationcited by 5
  34. 2026GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environmentscited by 5
  35. 2026GRADE: Benchmarking Discipline-Informed Reasoning in Image Editingcited by 5
  36. 2026ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Frameworkcited by 5
  37. 2026Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Eventscited by 5
  38. 2026RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generationcited by 5

50 most cited of 97 All 97 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
  2. 2025Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
  3. 2024EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing
  4. 2026GEditBench v2: A Human-Aligned Benchmark for General Image Editing
  5. 2025ReasonEdit: Towards Reasoning-Enhanced Image Editing Models
  6. 2026CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning
  7. 2025TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering
  8. 2026ETCHR: Editing To Clarify and Harness Reasoning