Computer Vision › Core AI ›

Efficient Computing

179 directly classified papers

Papers per year

Papers

Erasing Undesirable Influence in Diffusion Models CVPR 2025

Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks CVPR 2025

Column-Oriented Datalog on the GPU AAAI 2025

TurboVSR: Fantastic Video Upscalers and Where to Find Them ICCV 2025

FastVLM: Efficient Vision Encoding for Vision Language Models CVPR 2025

GradQ-ViT: Robust and Efficient Gradient Quantization for Vision Transformers AAAI 2025

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion NIPS 2024

Learning to Control Camera Exposure via Reinforcement Learning CVPR 2024

Exploring Token Pruning in Vision State Space Models NIPS 2024

Interference Aware Training Target for DNN based joint Acoustic Echo Cancellation and Noise Suppression INTERSPEECH 2024

HydraViT: Stacking Heads for a Scalable ViT NIPS 2024

UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer AAAI 2024

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers CVPR 2024

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution CVPR 2024

A Simple Baseline for Efficient Hand Mesh Reconstruction CVPR 2024

Bootstrapping SparseFormers from Vision Foundation Models CVPR 2024

Mixture of Nested Experts: Adaptive Processing of Visual Tokens NIPS 2024

Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective NIPS 2024

Accelerating Multilingual Language Model for Excessively Tokenized Languages ACL 2024

Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices NIPS 2024

CCMR: High Resolution Optical Flow Estimation via Coarse-To-Fine Context-Guided Motion Reasoning WACV 2024

Real-Time User-Guided Adaptive Colorization With Vision Transformer WACV 2024

SBCFormer: Lightweight Network Capable of Full-Size ImageNet Classification at 1 FPS on Single Board Computers WACV 2024

Visual Fourier Prompt Tuning NIPS 2024

SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design CVPR 2024