Skip to content

PaperCodex

Subscribe

Edge AI

YOLOv13: Boost Real-Time Object Detection Accuracy Without Sacrificing Speed or Efficiency

YOLOv13: Boost Real-Time Object Detection Accuracy Without Sacrificing Speed or Efficiency 827

For engineers, researchers, and product teams building real-time vision systems—whether for surveillance cameras, autonomous drones, or mobile apps—achieving high detection…

01/05/2026Edge AI, Object Detection, Real-time Computer Vision
RFBNet: High-Accuracy, Real-Time Object Detection Without Heavy Backbones

RFBNet: High-Accuracy, Real-Time Object Detection Without Heavy Backbones 1422

When building real-world computer vision systems—whether for autonomous drones, industrial inspection, or mobile apps—one of the toughest trade-offs is between…

12/27/2025Edge AI, Object Detection, Real-Time Inference
YOLOv6: Real-Time Object Detection Optimized for Speed, Accuracy, and Industrial Deployment

YOLOv6: Real-Time Object Detection Optimized for Speed, Accuracy, and Industrial Deployment 5869

YOLOv6 is a high-performance, single-stage object detection framework developed by Meituan with a strong emphasis on real-world industrial applications. Unlike…

12/26/2025Edge AI, Object Detection, Real-Time Inference
GhostNet: High-Accuracy Vision Models with Minimal Compute for Edge Deployment

GhostNet: High-Accuracy Vision Models with Minimal Compute for Edge Deployment 4355

Overview Deploying powerful computer vision models on resource-constrained devices—such as smartphones, IoT sensors, or drones—has long been a major engineering…

12/22/2025Edge AI, Image Classification, Object Detection
PP-PicoDet: Real-Time Object Detection with SOTA Accuracy on Mobile and Edge Devices

PP-PicoDet: Real-Time Object Detection with SOTA Accuracy on Mobile and Edge Devices 13974

In today’s era of intelligent edge computing, deploying high-performance computer vision models on resource-constrained devices like smartphones, embedded sensors, and…

12/18/2025Edge AI, Object Detection, Real-Time Inference
Mini-InternVL: Achieve 90% of Multimodal Performance with Just 5% of Model Size for Edge and Consumer Deployments

Mini-InternVL: Achieve 90% of Multimodal Performance with Just 5% of Model Size for Edge and Consumer Deployments 9328

In an era where multimodal large language models (MLLMs) are rapidly advancing, a critical barrier remains: most high-performing vision-language models…

12/18/2025Edge AI, Multimodal Reasoning, vision-language modeling
Parallax: Run LLMs on Decentralized Devices Without Costly GPU Clusters

Parallax: Run LLMs on Decentralized Devices Without Costly GPU Clusters 1004

Deploying large language models (LLMs) today often means relying on expensive, centralized infrastructure—specialized GPU clusters, high-bandwidth data centers, and recurring…

12/17/2025Decentralized Inference, Edge AI, Large Language Model Serving
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex