edge device

FedARA: Resource-adaptive Low-rank Personalized Federated Learning via Anchor-driven Representation Alignment on Heterogeneous Edge Devices CVPR 2026 HyperEdge: An Edge CDN Infrastructure for Cost Efficient Video Streaming NSDI 2026 NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration CVPR 2026 SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead CVPR 2026 AdaKWS: Towards Robust Keyword Spotting with Test-Time Adaptation Interspeech 2025 A New Benchmark and Baseline for Real-Time High-Resolution Image Inpainting on Edge Devices WACV 2025 AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning CVPR 2025 BackSlash: Rate Constrained Optimized Training of Large Language Models ICML 2025 Can't Slow Me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices CVPR 2025 Chain-of-Rank: Enhancing Large Language Models for Domain-Specific RAG in Edge Device NAACL 2025 Efficient Streaming Speech Quality Prediction with Spiking Neural Networks Interspeech 2025 Exploiting Label Skewness for Spiking Neural Networks in Federated Learning IJCAI 2025 FedSPU: Personalized Federated Learning for Resource-Constrained Devices with Stochastic Parameter Update AAAI 2025 MKD: Multi-Knowledge Distillation for Real-Time Object Detection on Edge Devices ACML 2025 OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning ICCV 2025 QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache ICML 2025 SIDC-KWS: Efficient Spiking Inception-Dilated Conformer with Self-Attention for Keyword Spotting Interspeech 2025 Sparse Structure Exploration and Re-optimization for Vision Transformer UAI 2025 TargetVoice: Single Channel Low-Latency Target Speaker Extraction Interspeech 2025 TinyFoA: Memory Efficient Forward-Only Algorithm for On-Device Learning AAAI 2025 Continual Learning in the Frequency Domain NeurIPS 2024 Countering the Communication Bottleneck in Federated Learning: A Highly Efficient Zero-Order Optimization Technique JMLR 2024 Efficient Look-Up Table from Expanded Convolutional Network for Accelerating Image Super-resolution AAAI 2024 FITS: Modeling Time Series with $10k$ Parameters ICLR 2024 Gradient Coreset for Federated Learning WACV 2024