arXiv Machine Learning

CARE: Condition-Aware Representation Regularization for Diffusion Models

The paper introduces CARE, a lightweight, plug‑and‑play regularization framework for diffusion models that dynamically adjusts feature distributions based on condition similarity. By leveraging built‑in conditioning signals such as labels or text prompts, CARE promotes tighter feature clusters for similar conditions without requiring explicit alignment losses or external supervision. Empirical results show consistent improvements in visual fidelity and convergence stability, achieving significant FID reductions and speed‑ups on ImageNet and text‑to‑image tasks, and it can be combined with existing regularization methods for further gains.

arXiv Computer Vision

Sep 11

AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow

AcFlow introduces an inference‑time controller for text‑to‑image diffusion transformers that transports intermediate layer activations through a learned, concept‑conditioned velocity field while keeping the base model frozen. The method allows fine‑grained style intensity control and suppression of unwanted concepts, achieving superior style–content trade‑offs compared to baselines and generalizing to unseen concepts without per‑concept fitting. Experiments demonstrate improved style alignment and qualitative suppression of diverse concepts where direct prompting fails.

By Junran Wang, Zehao Jin, Tianyu Luan, Xinjie Shen

llms diffusion safety

arXiv Machine Learning

Sep 1

TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimization

arXiv:2511.19811v2 Announce Type: replace-cross Abstract: Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity generation often leads to repetitive output...

By Debin Meng, Chen Jin, Zheng Gao, Yanran Li, Ioannis Patras, Georgios Tzimiropoulos

rag diffusion

arXiv AI

2d ago

Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers

arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas th...

By Xiaoyu Wu, Yifei Wang, Chen Wei

llms diffusion computer-vision safety

arXiv AI

1d ago

ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

ReGain is a training‑free correction that improves subject fidelity in text‑to‑image diffusion models personalized with synthetic images. The authors show that fine‑tuning on synthetic images degrades fidelity due to inflated classifier‑free guidance, especially at high frequencies. ReGain measures this inflation per frequency band and scales it down during sampling, closing 51‑64% of the fidelity gap on Stable Diffusion v1.5 and improving performance on SDXL and SD 3.5 while preserving text alignment.

By Shubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah, Narendra Ahuja

diffusion fine-tuning safety

Hugging Face Trending Papers

Jun 19

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain available for training. One of the promising directions for achieving single-domain generalization is to generate out-of-domain (OOD) training data through data augmentation or image generation.

diffusion benchmarks safety

arXiv AI

Jul 8

TILDE: TILt-based Distributional Erasure for Concept Unlearning

arXiv:2607. 06432v1 Announce Type: cross Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training.

By Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji

diffusion safety

arXiv AI

Jun 2

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models

arXiv:2603. 00133v2 Announce Type: replace-cross Abstract: Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement.

By Kairan Zhao, Eleni Triantafillou, Peter Triantafillou

diffusion benchmarks safety

arXiv AI

Jun 2

Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching

arXiv:2602. 05951v2 Announce Type: replace-cross Abstract: Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation.

By Junwan Kim, Jiho Park, Seonghu Jeon, Seungryong Kim

diffusion benchmarks safety

arXiv Machine Learning

Jul 9

Gen4U: Unifying Video Generation and Understanding via Diffusion

arXiv:2607. 06856v1 Announce Type: cross Abstract: Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics.

By Michael King, Aravindh Mahendran, Matthew Koichi Grimes, Fedor Kitashov, Adham Elarabawy, Pedro Velez, Maks Ovsjanikov, Viorica P\u{a}tr\u{a}ucean

diffusion computer-vision fine-tuning benchmarks safety

arXiv Computer Vision

Aug 26

ASemConsist: Adaptive Semantic Feature Control for Training-Free Identity-Consistent Generation

arXiv:2512.23245v3 Announce Type: replace Abstract: Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while...

By Shin Seong Kim, Minjung Shin, Hyunin Cho, Youngjung Uh

rag diffusion benchmarks safety

Hugging Face Trending Papers

Aug 17

PixRestore: Unified Image Restoration via Pixel Diffusion Transformer

Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.

llms diffusion benchmarks safety

arXiv AI

Jun 2

Improving Visual Representation Alignment Generation with GRPO

arXiv:2606. 00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations.

By Shentong Mo, Sukmin Yun

llms rag diffusion safety

Related stories