Model Compression

ECCV 2024arXiv:2403.19522

#2

Model Stock: All we need is just a few fine-tuned models

Dong-Hwan Jang, Sangdoo Yun, Dongyoon Han

71

CVPR 2025arXiv:2503.12461

#3

MambaIC: State Space Models for High-Performance Learned Image Compression

Fanhu Zeng, Hao Tang, Yihua Shao et al.

14

ICML 2025arXiv:2410.05078

#4

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)

Tianyi Zhang, Mohsen Hariri, Shaochen (Henry) Zhong et al.

You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning

Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty

Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data

David Heurtel-Depeiges, Anian Ruoss, Joel Veness et al.

7

ICCV 2025arXiv:2503.14237

#7

Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models

Xuran Ma, Yexin Liu, Yaofu LIU et al.

Make Your Training Flexible: Towards Deployment-Efficient Video Models

Chenting Wang, Kunchang Li, Tianxiang Jiang et al.

5

CVPR 2025arXiv:2503.13385

#9

Scale Efficient Training for Large Datasets

Qing Zhou, Junyu Gao, Qi Wang

3

AAAI 2025arXiv:2412.17387

#10

Scaling Down Text Encoders of Text-to-Image Diffusion Models

Lifu Wang, Daqing Liu, Xinchen Liu et al.

Test-Time Fine-Tuning of Image Compression Models for Multi-Task Adaptability

Unki Park, Seongmoon Jeong, Jang Youngchan et al.

DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge

Sabbir Ahmed, Abdullah Al Arafat, Deniz Najafi et al.

Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement

Hyeonjin Kim, Jaejun Yoo

2

ICCV 2025arXiv:2405.15034

#14

Neural Compression for 3D Geometry Sets

Siyu Ren, Junhui Hou, Weiyao Lin et al.

neural compression3d geometry setsimplicit representationtsdf-def+4

1

ICCV 2025arXiv:2409.17564

#15

Scaling Mesh Generation via Compressive Tokenization

Haohan Weng, Zibo Zhao, Biwen Lei et al.

Tiny Models are the Computational Saver for Large Models

Qingyuan Wang, Barry Cardiff, Antoine Frappé et al.

Less is More: Efficient Model Merging with Binary Task Switch

Biqing Qi, Fangyuan Li, Zhen Wang et al.

General Compression Framework for Efficient Transformer Object Tracking

Lingyi Hong, Jinglun Li, Xinyu Zhou et al.

ICML 2024arXiv:2403.09636

#19

Data Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance

Dong Chen, Yueting Zhuang, Shuo Zhang et al.

Forget the Data and Fine-Tuning! Just Fold the Network to Compress

Dong Wang, Haris Šikić, Lothar Thiele et al.

Slice-and-Pack: Tailoring Deep Models for Customized Requirements

Ruice Rao, Dingwei Li, Ming Li

Compress to One Point: Neural Collapse for Pre-Trained Model-Based Class-Incremental Learning

Kun Wei, Zhe Xu, Cheng Deng

EvoPress: Accurate Dynamic Model Compression via Evolutionary Search

Oliver Sieberling, Denis Kuznedelev, Eldar Kurtic et al.

Resource-Efficient Transformer Pruning for Finetuning of Large Models

Fatih Ilhan, Gong Su, Selim Tekin et al.

Language Modeling Is Compression

Gregoire Deletang, Anian Ruoss, Paul-Ambroise Duquenne et al.

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Piotr Nawrot, Adrian Łańcucki, Marcin Chochowski et al.

key-value cache compressioninference time optimizationtransformer architectureautoregressive generation+3

structured pruningknowledge distillationweight sharingzero-shot pruning+4

#27

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

Ruisi Cai, Saurav Muralidharan, Hongxu Yin et al.

ICLR 2025

model compressiongradient reweightingpruning efficiencylarge language models+3

#28

Computation and Memory-Efficient Model Compression with Gradient Reweighting

Zhiwei Li, Yuesen Liao, Binrui Wu et al.

NeurIPS 2025

NeurIPS 2025arXiv:2507.17511

#29

Accelerating Parallel Diffusion Model Serving with Residual Compression

Jiajun Luo, Yicheng Xiao, Jianru Xu et al.

diffusion model servingresidual compressionparallel inferenceactivation redundancy+4

#30

Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism

Sameera Ramasinghe, Thalaiyasingam Ajanthan, Gil Avraham et al.

MCNC: Manifold-Constrained Reparameterization for Neural Compression

Chayne Thrash, Reed Andreas, Ali Abbasi et al.

ICLR 2025