conftrace_

edge deployment

58 papers

Explore in graph

Co-occurring keywords

model compression (3302) knowledge distillation (3725) edge computing (210) model quantization (281) vision transformer (1106) weight quantization (137) efficient computing (781) small language model (204) large language model (13587) neural network (6616)

Papers

SPEED-Q: Staged Processing with Enhanced Distillation Towards Efficient Low-Bit On-Device VLM Quantization AAAI 2026
Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems ACL 2026
Towards Robust Edge Model Adaptation via Elastic Architecture Search AAAI 2026
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model AAAI 2026
FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation WACV 2026
FIRM-MoE:Fine-GrainedExpert Decomposition for Resource-Adaptive MoE Inference AAAI 2026
Deploying Rapid Damage Assessments from sUAS Imagery for Disaster Response AAAI 2026
EASE: Practical and Efficient Safety Alignment for Small Language Models AAAI 2026
EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration ACL 2026
RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Linguistic Classifiers COLING 2025
Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control ICCV 2025
GradQ-ViT: Robust and Efficient Gradient Quantization for Vision Transformers AAAI 2025
Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels ICCV 2025
Demystifying Small Language Models for Edge Deployment ACL 2025
DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables CVPR 2025
Grammar Pruning: Enabling Low-Latency Zero-Shot Task-Oriented Language Models for Edge AI EMNLP 2025
AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning CVPR 2025
MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks CVPR 2025
ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025
Boost Embodied AI Models with Robust Compression Boundary IJCAI 2025
VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers AAAI 2025
JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration AAAI 2025
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices EMNLP 2025
MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge ICCV 2025
Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge WACV 2025