#Edge computing

Articles (4)

• 🇺🇸 BiKA: Kolmogorov-Arnold-Network-inspired Ultra Lightweight Neural Network Hardware Accelerator — 02/03/2026 [USA]

  arXiv:2602.23455v1 Announce Type: cross Abstract: Lightweight neural network accelerators are essential for edge devices with limited resources and power constraints. While quantization and binarizat...

  Related: #Artificial intelligence hardware, #Lightweight neural networks, #FPGA acceleration, #Quantization and binarization
• 🇺🇸 Co-founders behind Reface and Prisma join hands to improve on-device model inference with Mirai — 19/02/2026 [USA]

  Mirai raised a $10 million seed to improve how AI models run on devices like smartphones and laptops.

  Related: #On‑device AI, #Startup collaboration, #AI performance optimization, #Privacy‑focused tech
• 🇺🇸 Edge Learning via Federated Split Decision Transformers for Metaverse Resource Allocation — 19/02/2026 [USA]

  arXiv:2602.16174v1 Announce Type: cross Abstract: Mobile edge computing (MEC) based wireless metaverse services offer an untethered, immersive experience to users, where the superior quality of exper...

  Related: #Federated learning, #Metaverse, #Virtual reality, #Resource allocation
• 🇺🇸 EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices — 19/02/2026 [USA]

  arXiv:2602.15836v1 Announce Type: cross Abstract: Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control. However, de...

  Related: #Large Action Models, #Autonomous navigation, #Model quantization, #Dynamic early exit