paper-with-me

Papers

Importance-Aware OBS Pruning for Diffusion Models

2026-07-22 · Ba-Thinh Lam, Srijan Das, Hieu Le arxiv

We propose importance-aware pruning for diffusion models, a training-free framework that prioritizes preserving parameters critical to semantically salient image regions. To do so, we incorporate spatial importance maps -- derived from conditioning signals or model attention -- into the pruning objective. This produces parameter rankings aligned with perceptual relevance rather than uniform reconstruction error. On MS-COCO dataset, our proposed approach consistently retains subject fidelity and structural correctness at high compression ratios where conventional pruning causes visible degradation. These results demonstrate that content-aware objectives are key to perceptually faithful compression of generative models.

📄 PDF Abstract BibTeX arXiv:2607.20048

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Temporal Aware Pruning for Efficient Diffusion-based Video Generation

2026-05-18 · Sheng Li, Yang Sui, Junhao Ran, Bo Yuan 외 arxiv

Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal seq…

Video Generation

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

2025-10-08 · Junhan Zhu, Hesong Wang, Mingluo Su, Zefang Wang 외 arxiv

Large-scale text-to-image diffusion models, while powerful, suffer from prohibitive computational cost. Existing one-shot network pruning methods can hardly be directly applied to them due to the iterative denoising natu…

Network Pruning

FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification

2022-07-22 · Xiaofeng Lin, Seungbae Kim, Jungseock Joo

Existing pruning techniques preserve deep neural networks' overall ability to make correct predictions but may also amplify hidden biases during the compression process. We propose a novel pruning method, Fairness-aware …

AttributeFairness

Sample-aware Adaptive Structured Pruning for Large Language Models

2025-03-08 · Jun Kong, Xinge Ma, Jin Wang, Xuejie Zhang

Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectivel…

Bayesian Optimization

Sink-Aware Pruning for Diffusion Language Models

2026-02-19 · Aidar Myrzakhan, Tianyi Li, Bowei Guo, Shengkun Tang 외 arxiv

Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited from autoregressive (AR) LLMs, typically preserve attenti…