mlsanityData to 14 Oct 2026

Generating on Generated: An Approach Towards Self-Evolving Diffusion Models

arXiv 2502.09963 ↗First posted 14 Feb 2025cs.CVcited by 3

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by synthetic data. We identify two key factors contributing to this collapse: the lack of perceptual alignment and the accumulation of generative hallucinations. To mitigate these issues, we propose three strategies: (1) a prompt construction and filtering pipeline designed to facilitate the generation of perceptual aligned data, (2) a preference sampling method to identify human-preferred samples and filter out generative hallucinations, and (3) a distribution-based weighting scheme to penalize selected samples with hallucinatory errors. Our extensive experiments validate the effectiveness of these approaches.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 19 of its 43 references that are in the map. First posted on arXiv 14 Feb 2025.

Builds on

19 of 43 references.

References · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  6. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  7. 2023Teaching Large Language Models to Self-Debugcited by 988
  8. 2023Training Diffusion Models with Reinforcement Learningcited by 982
  9. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  10. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  11. 2024Self-Rewarding Language Modelscited by 681
  12. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 557
7 more
  1. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 279
  2. 2023Self-Consuming Generative Models Go MADcited by 250
  3. 2023SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoningcited by 159
  4. 2024A Survey on Self-Evolution of Large Language Modelscited by 91
  5. 2024Strong Model Collapsecited by 65
  6. 2013Bounded Recursive Self-Improvementcited by 10
  7. 2015From Seed AI to Technological Singularity via Recursively Self-Improving Softwarecited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2026Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loopscited by 35
  2. 2025A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspectivecited by 18
  3. 2025Epistemic diversity across language models mitigates knowledge collapsecited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Score-Control for Hallucination Reduction in Diffusion Models
  2. 2026Hallucination Early Detection in Diffusion Models
  3. 2025Mitigating Diffusion Model Hallucinations with Dynamic Guidance
  4. 2025Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
  5. 2025Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation
  6. 2024Optimizing Resource Consumption in Diffusion Models through Hallucination Early Detection
  7. 2025Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
  8. 2024Generative AI in Vision: A Survey on Models, Metrics and Applications