paper-with-me

Papers

Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance

2026-06-25 · Pradhaan S Bhat, Rishubh Parihar, Abhijnya Bhat, R. Venkatesh Babu arxiv

State-of-the-art flow models generate stunning images from text or image prompts. However, they suffer from diversity collapse when generating multiple samples under the same conditioning. Existing methods address this issue via either latent guidance, which has limited effectiveness, or sample selection, which relies on external reward models that incur significant inference-time overhead. In this work, we introduce an efficient, training-free self-guidance mechanism to mitigate diversity collapse without requiring additional reward models. Specifically, we disperse the internal features of the flow model during batch generation with feature self-guidance. Further, to keep the features close to the manifold, we introduce a manifold regularization step that projects these dispersed features back onto the data manifold, ensuring diverse generation without sacrificing alignment with the input conditions. Our method integrates seamlessly as a plug-and-play module into pretrained flow models, adding only a marginal inference cost. Experiments demonstrate significant improvements in diversity while preserving fidelity across several conditional flow models, including multi-step and few-step text-to-image, depth-to-image, and reference image generation.

📄 PDF Abstract BibTeX arXiv:2606.27371

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Self-Feedback DETR for Temporal Action Detection

2023-08-21 · ICCV 2023 1 · JiHwan Kim, Miso Lee, Jae-Pil Heo

Temporal Action Detection (TAD) is challenging but fundamental for real-world video applications. Recently, DETR-based models have been devised for TAD but have not performed well yet. In this paper, we point out the pro…

Action DetectionDecoderDiversity

Epistemic diversity across language models mitigates knowledge collapse

2025-12-17 · Damian Hodel, Jevin D. West arxiv

As artificial intelligence (AI) becomes more widely used, concerns are growing that model collapse could lead to knowledge collapse, i.e. a degradation to a narrow and inaccurate set of ideas. Prior work has demonstrated…

Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation

2026-01-18 · Jinmei Liu, Haoru Li, Zhenhong Sun, Chaofeng Chen 외 arxiv

Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks. A fundame…

Reinforcement LearningImage Generation

Mapping Rio de Janeiro's favelas: general-purpose vs. satellite-specific neural networks

2025-10-04 · Thomas Hallopeau, Joris Guérin, Laurent Demagistri, Youssef Fouzai 외 arxiv

While deep learning methods for detecting informal settlements have already been developed, they have not yet fully utilized the potential offered by recent pretrained neural networks. We compare two types of pretrained …

Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control

2024-02-23 · Masatoshi Uehara, Yulai Zhao, Kevin Black, Ehsan Hajiramezanali 외

Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in the training dataset, we often are more co…

Diversity