arXiv Computer Vision September 28, 2026 By Ba-Thinh Lam, Srijan Das, Hieu Le

Importance-Aware OBS Pruning for Diffusion Models

Read the original on arXiv Computer Vision →

The paper introduces an importance-aware pruning method for diffusion models that is training‑free and focuses on preserving parameters essential to semantically salient image regions. By integrating spatial importance maps derived from conditioning signals or model attention into the pruning objective, the method generates parameter rankings that reflect perceptual relevance rather than uniform reconstruction error. Experiments on the MS‑COCO dataset show that this approach maintains subject fidelity and structural correctness even at high compression ratios, outperforming conventional pruning techniques that cause visible degradation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

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

Jul 2

Post-Training Pruning for Diffusion Transformers

arXiv:2607. 00927v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption.

By Chengzhi Hu, Xuewen Liu, Jing Zhang, Mengjuan Chen, Zhikai Li, Qingyi Gu

llms diffusion efficiency

arXiv Machine Learning

Sep 25

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.

By Fengjia Guo, Zhuoyi Yang, Jie Tang

diffusion 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 Computer Vision

Sep 30

Representation Dynamics Reveal Semantic Saliency and Similarity for Visual Token Pruning in MLLMs

arXiv:2609.36916v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur high inference latency from long visual token sequences. Existing pruning methods commonly use attention...

By Weixuan Li, Zikun Zhou, Xinyi Zhuang, Xinyan Guo, Rui Tian, Chuyao Zhang, Lin Gao

llms efficiency multimodal

arXiv AI

Jun 9

RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT

arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.

By Kyumin Choi, Ikbeom Jang

llms efficiency