← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration CVPR 2025
DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization ICCV 2025
GAP: a Global Adaptive Pruning Method for Large Language Models EMNLP 2025
Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection ICCV 2025
Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation CVPR 2025
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model CVPR 2025
FlashSloth : Lightning Multimodal Large Language Models via Embedded Visual Compression CVPR 2025
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks CVPR 2025
Task-Specific Zero-shot Quantization-Aware Training for Object Detection ICCV 2025
ICP: Immediate Compensation Pruning for Mid-to-high Sparsity CVPR 2025
Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model CVPR 2025
ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints ICCV 2025
ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025
OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models ICCV 2025
Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? CVPR 2025
Dataset Distillation with Neural Characteristic Function: A Minmax Perspective CVPR 2025
Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping ICCV 2025
Knowledge Distillation for Learned Image Compression ICCV 2025
Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing CVPR 2025
SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting ICCV 2025
Mobile Video Diffusion ICCV 2025
ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models ICCV 2025
FOLDER: Accelerating Multi-Modal Large Language Models with Enhanced Performance ICCV 2025
Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation ICCV 2025
MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics ICCV 2025