Nota AI

Cluster Self-refinement for Enhanced Online Multi-camera People Tracking

Algorithms & Models, Blog Posts, Nota AI, Object Identification, Object Tracking, Software, Tools /

This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. Online multi-camera system for efficient individual tracking Accurate ID management with Cluster Self-Refinement (CSR) Improved performance with enhanced pose estimation In this paper, we introduce our online MCPT methodology, which achieved third place in Track1 […]

Cluster Self-refinement for Enhanced Online Multi-camera People Tracking Read More +

SplitQuant: Layer Splitting for Low-bit Neural Network Quantization for Edge AI Devices

Algorithms & Models, Blog Posts, Nota AI, Software, Tools /

This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. This study proposes an AI model preprocessing method for improved quantization accuracies on edge AI devices which do not support advanced quantization methods due to their limitations. By splitting layers based on parameter clustering, the

SplitQuant: Layer Splitting for Low-bit Neural Network Quantization for Edge AI Devices Read More +

Nota AI and Wind River Collaborate to Deliver On-device Generative AI for the Intelligent Edge

Algorithms & Models, News, Nota AI, Software, Tools /

SEOUL, South Korea and ALAMEDA, CA – May 28, 2025 – Nota AI, a pioneer in on-device AI optimization, and Wind River, a global leader in delivering software for the intelligent edge, have signed a strategic Partner Program Agreement (PPA) to combine Nota AI’s NetsPresso® capabilities into Wind River Studio Developer. “The combination of technologies

Nota AI and Wind River Collaborate to Deliver On-device Generative AI for the Intelligent Edge Read More +

UniForm: A Reuse Attention Mechanism for Efficient Transformers on Resource-constrained Edge Devices

Algorithms & Models, Blog Posts, Nota AI, Software, Tools /

This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. Delivers real-time AI performance on edge devices such as smartphones, IoT devices, and embedded systems. Introduces a novel “Reuse Attention” technique that minimizes redundant computations in Multi-Head Attention. Achieves competitive accuracy and significant inference speed

UniForm: A Reuse Attention Mechanism for Efficient Transformers on Resource-constrained Edge Devices Read More +

Nota AI Demonstrates On-device AI Breakthrough at Embedded Vision Summit 2025 in Collaboration with Qualcomm AI Hub

News, Nota AI, Tools /

NetsPresso® and Qualcomm AI Hub: Strategic Integration Streamlines Edge AI Development Generative AI solutions drive global expansion momentum ahead of IPO listing SEOUL, South Korea, May 26, 2025 /PRNewswire/ — Nota AI, a global leader in AI optimization, showcased its latest edge AI innovations alongside Qualcomm Technologies, Inc. at the Embedded Vision Summit 2025, held

Nota AI Demonstrates On-device AI Breakthrough at Embedded Vision Summit 2025 in Collaboration with Qualcomm AI Hub Read More +

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

Algorithms & Models, Blog Posts, Multimodal, Nota AI, Software, Tools /

This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. Our method, Trimmed-Llama, reduces the key-value cache (KV cache) and latency of cross-attention-based Large Vision Language Models (LVLMs) without sacrificing performance. We identify sparsity in LVLM cross-attention maps, showing a consistent layer-wise pattern where most

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features Read More +

Deploying an Efficient Vision-Language Model on Mobile Devices

Algorithms & Models, Blog Posts, Multimodal, Nota AI, Software, Tools /

This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. Recent large language models (LLMs) have demonstrated unprecedented performance in a variety of natural language processing (NLP) tasks. Thanks to their versatile language processing capabilities, it has become possible to develop various NLP applications that

Deploying an Efficient Vision-Language Model on Mobile Devices Read More +

Nota AI Supports Qualcomm AI Hub with On-device Generative AI, Proving Global Technological Prowess

News, Nota AI /

The on-device generative AI optimization platform NetsPresso® supports AI model optimization on Qualcomm processors through the Qualcomm AI Hub Earns dual ‘A’ ratings in technical evaluation signaling strong IPO prospects SEOUL, South Korea, Feb. 21, 2025 /PRNewswire/ — Nota AI, a leader in on-device AI optimization, is strengthening its global footprint in IoT and edge

Nota AI Supports Qualcomm AI Hub with On-device Generative AI, Proving Global Technological Prowess Read More +

Alliance Members at 2025 CES

AiM Future, Airy3D, Au-Zone Technologies, Axelera AI, BrainChip, Cadence, Ceva, CLIKA, Commonlands, D3 Embedded, DEEPX, Digica, e-con Systems, Edge AI and Vision Alliance, Embedl, ENERZAi, eYs3D Microelectronics, Geisel Software, Gimlet Labs, Hailo, Inuitive, Microchip Technology, News, Nextchip, Nota AI, NXP Semiconductors, OpenMV, Piera Systems, Quadric, Texas Instruments, VeriSilicon, videantis, Visionary.ai /

The Edge AI and Vision Alliance 2025 CES Directory for game-changing computer vision and AI technologies Many Alliance Member companies will be showing off the latest building-block technologies that enable new capabilities for machines that see! CES is huge so we’ve created a handy checklist of these companies and where to find them including how

Alliance Members at 2025 CES Read More +

Nota AI Demonstration of Transforming Edge AI with the LaunchX Converter and Benchmarker

Algorithms & Models, Nota AI, Software, Summit 2024, Tools, Videos /

Tae-Ho Kim, CTO and Co-founder of Nota AI, demonstrates the company’s latest edge AI and vision technologies and products at the 2024 Embedded Vision Summit. Specifically, Kim demonstrates his company’s LaunchX platform, featuring its powerful Converter and Benchmarker. LaunchX optimizes AI models for edge devices, reducing latency and boosting performance. Practical applications of the Converter

Nota AI Demonstration of Transforming Edge AI with the LaunchX Converter and Benchmarker Read More +

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Pages

Topics

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top