"model pruning" Papers

21 papers found

Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective

Weizhong Huang, Yuxin Zhang, Xiawu Zheng et al.

NEURIPS 2025

Discovering Influential Neuron Path in Vision Transformers

Yifan Wang, Yifei Liu, Yingdong Shi et al.

ICLR 2025arXiv:2503.09046
4
citations

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

Xinyu Zhou, Tongxin Pan, Lingyi Hong et al.

NEURIPS 2025arXiv:2510.21351

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training

Lexington Whalen, Zhenbang Du, Haoran You et al.

CVPR 2025arXiv:2504.09606
2
citations

FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling

Hong Huang, Jinhai Yang, Yuan Chen et al.

NEURIPS 2025arXiv:2501.19122
4
citations

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

Hadi Askari, Shivanshu Gupta, Fei Wang et al.

NEURIPS 2025arXiv:2505.23811
6
citations

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

Pengxiang Li, Lu Yin, Shiwei Liu

ICLR 2025arXiv:2412.13795
26
citations

Mobile Video Diffusion

Haitam Ben Yahia, Denis Korzhenkov, Ioannis Lelekas et al.

ICCV 2025arXiv:2412.07583
12
citations

On-Device Diffusion Transformer Policy for Efficient Robot Manipulation

Yiming Wu, Huan Wang, Zhenghao Chen et al.

ICCV 2025arXiv:2508.00697
2
citations

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training

Weiyu Huang, Yuezhou Hu, Guohao Jian et al.

AAAI 2025paperarXiv:2407.20584
21
citations

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

Teng Hu, Jiangning Zhang, Ran Yi et al.

ICLR 2025arXiv:2409.06633
1
citations

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts

Mohammed Nowaz Rabbani Chowdhury, Meng Wang, Kaoutar El Maghraoui et al.

ICML 2024arXiv:2405.16646
10
citations

COPAL: Continual Pruning in Large Language Generative Models

Srikanth Malla, Joon Hee Choi, Chiho Choi

ICML 2024arXiv:2405.02347
6
citations

FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing

Yongzhe Jia, Xuyun Zhang, Amin Beheshti et al.

AAAI 2024paperarXiv:2402.08578
11
citations

How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?

Hongkang Li, Meng Wang, Songtao Lu et al.

ICML 2024arXiv:2402.15607
34
citations

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs

Lu Yin, Ajay Jaiswal, Shiwei Liu et al.

ICML 2024

Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection

Alireza Ganjdanesh, Yan Kang, Yuchen Liu et al.

ECCV 2024arXiv:2409.15557
12
citations

Non-transferable Pruning

Ruyi Ding, Lili Su, A. Adam Ding et al.

ECCV 2024arXiv:2410.08015
4
citations

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Lu Yin, You Wu, Zhenyu Zhang et al.

ICML 2024arXiv:2310.05175
152
citations

Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities

Stephen Zhang, Vardan Papyan

ICML 2024arXiv:2407.04075

Unveiling the Dynamics of Information Interplay in Supervised Learning

Kun Song, Zhiquan Tan, Bochao Zou et al.

ICML 2024arXiv:2406.03999
3
citations