mlsanityData to 14 Oct 2026

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking

arXiv 2603.20785 ↗First posted 21 Mar 2026cs.CVcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Reasoning-induced vision-language models (VLMs) advance image quality assessment (IQA) with textual reasoning, yet their scalar scores often lack sensitivity and collapse to a few values, so-called discrete collapse. We introduce ME-IQA, a plug-and-play, test-time memory-enhanced re-ranking framework. It (i) builds a memory bank and retrieves semantically and perceptually aligned neighbors using reasoning summaries, (ii) reframes the VLM as a probabilistic comparator to obtain pairwise preference probabilities and fuse this ordinal evidence with the initial score under Thurstone's Case V model, and (iii) performs gated reflection and consolidates memory to improve future decisions. This yields denser, distortion-sensitive predictions and mitigates discrete collapse. Experiments across multiple IQA benchmarks show consistent gains over strong reasoning-induced VLM baselines, existing non-reasoning IQA methods, and test-time scaling alternatives.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 51 of its 80 references that are in the map. First posted on arXiv 21 Mar 2026.

Builds on

51 of 80 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank20 May

Other references · 50

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  7. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  8. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  9. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  10. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  11. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  12. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
38 more
  1. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  2. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  3. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  4. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  5. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  6. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 547
  7. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  8. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  9. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 480
  10. 2017NIMA: Neural Image Assessmentcited by 389
  11. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 355
  12. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 284
  13. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  14. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 254
  15. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
  16. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 209
  17. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 187
  18. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 178
  19. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  20. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 141
  21. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  22. 2022Retrieval-Augmented Multimodal Language Modelingcited by 125
  23. 2022REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memorycited by 123
  24. 2025Inducing Programmatic Skills for Agentic Taskscited by 111
  25. 2023Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Modelscited by 105
  26. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learningcited by 98
  27. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 95
  28. 2019dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairscited by 73
  29. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
  30. 2025M+: Extending MemoryLLM with Scalable Long-Term Memorycited by 54
  31. 2024StreamBench: Towards Benchmarking Continuous Improvement of Language Agentscited by 47
  32. 2021Continual Learning for Blind Image Quality Assessmentcited by 36
  33. 2013Learning to Rank for Blind Image Quality Assessmentcited by 25
  34. 2020Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessmentcited by 24
  35. 2025PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Processcited by 18
  36. 2021Troubleshooting Blind Image Quality Models in the Wildcited by 14
  37. 2025Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Rankingcited by 10
  38. 2023Regression-free Blind Image Quality Assessment with Content-Distortion Consistencycited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning
  2. 2025Revisiting MLLM Based Image Quality Assessment: Errors and Remedy
  3. 2026Q-Tacit: Image Quality Assessment via Latent Visual Reasoning
  4. 2026MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment
  5. 2025Building Reasonable Inference for Vision-Language Models in Blind Image Quality Assessment
  6. 2026From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment
  7. 2025Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
  8. 2026IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment