← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive Mixed-Precision Post-Training Quantization WACV 2025
SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation WACV 2025
Data Generation for Hardware-Friendly Post-Training Quantization WACV 2025
LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones WACV 2025
TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration WACV 2025
eLIR-Net: An Efficient AI Solution for Image Retouching WACV 2025
SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models WACV 2025
Advancing Weight and Channel Sparsification with Enhanced Saliency WACV 2025
Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025
Vocabulary-level Memory Efficiency for Language Model Fine-tuning NAACL 2025
AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model ICCV 2025
Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning ICCV 2025
Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels ICCV 2025
MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics ICCV 2025
DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization ICCV 2025
Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation ICCV 2025
ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models ICCV 2025
DAViD: Data-efficient and Accurate Vision Models from Synthetic Data ICCV 2025
AIRA: Activation-Informed Low-Rank Adaptation for Large Models ICCV 2025
LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models NAACL 2025
Block Circulant Adapter for Large Language Models IJCAI 2025
BitNet: 1-bit Pre-training for Large Language Models JMLR 2025
Slender-Mamba: Fully Quantized Mamba in 1.58 Bits From Head to Toe COLING 2025
Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings COLING 2025
Emulating Self-attention with Convolution for Efficient Image Super-Resolution ICCV 2025