mlsanityData to 7 Oct 2026

Image editing and quality assessment

202 papers1 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: editing, quality, image, diffusion, assessment

Key facts. Image editing and quality assessment: 202 papers on arXiv since 2021 (data through 7 Oct 2026). 15 of its 202 mapped papers (7%) cite “Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models” (2023, arXiv 2312.08962). 12 of its 202 mapped papers (6%) cite “Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution” (2025, arXiv 2501.11561). 5 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

5 new papers, 17 Sep – 7 Oct; 1 this week.

  1. This week · 1
  2. Self-correction Optimization for Interleaved Multimodal Generation also fits: MLLM training and visual instruction tuning
  3. Earlier · 4
  4. Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation
  5. Evaluating the Evaluators: Diagnosing Large Multimodal Models for AI-Generated Image Assessment
  6. FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching
  7. ControlTrace: Recovering Control Fields for Hidden-Content Recognition also fits: Prompt learning and adaptation of CLIP

Foundations

Most cited by papers here

  1. Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models2023cited by 15 here
  2. Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution2025cited by 12 here
  3. AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception2024cited by 9 here
  4. AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception2024cited by 8 here
  5. A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment2024cited by 8 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 8 here
  2. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 17 here
  3. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 16 here
  4. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 7 here
  5. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 14 here
  6. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessmentcited by 8 here
  7. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 7 here
17 more it builds on, not in this chain
  1. 2023Generating Images with Multimodal Language Modelscited by 8 here
  2. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 9 here
  3. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 6 here
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 12 here
  5. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 6 here
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 19 here
  7. 2023Can We Edit Multimodal Large Language Models?cited by 8 here
  8. 2023Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Modelscited by 15 here
  9. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 9 here
  10. 2024AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perceptioncited by 8 here
  11. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmarkcited by 6 here
  12. 2024AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perceptioncited by 9 here
  13. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 8 here
  14. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 16 here
  15. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 12 here
  16. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 6 here
  17. 2025Qwen3-VL Technical Reportcited by 7 here

The 24 most cited of 314.

Browse

30 of 202, ranked 6–35

  1. 6Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare20247
  2. 7VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark20246
  3. 8Controlling Vision-Language Models for Multi-Task Image Restoration20236
  4. 92AFC Prompting of Large Multimodal Models for Image Quality Assessment20245
  5. 10MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing20245
  6. 11Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset20245
  7. 12MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency20245
  8. 13VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining20235
  9. 14Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding20254
  10. 15SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning20244
All 30
  1. 16Guiding Instruction-based Image Editing via Multimodal Large Language Models20234
  2. 17LaViDa: A Large Diffusion Language Model for Multimodal Understanding20253
  3. 18VisualCritic: Making LMMs Perceive Visual Quality Like Humans20243
  4. 19Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit20243
  5. 20Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models20243
  6. 21Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts20243
  7. 22SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models20233
  8. 23Multimodal LLMs Can Reason about Aesthetics in Zero-Shot20252
  9. 24BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing20252
  10. 25ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images20252
  11. 26AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment20252
  12. 27UniFusion: Vision-Language Model as Unified Encoder in Image Generation20252
  13. 28Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs20242
  14. 29UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment20242
  15. 30RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models20242
  16. 31LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models20242
  17. 32Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration20242
  18. 33Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model20251
  19. 34Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens20251
  20. 35ImgEdit: A Unified Image Editing Dataset and Benchmark20251