Algorithms & Models

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models

This blog post was originally published at Nota AI’s website. It is reprinted here with the permission of Nota AI. Key Takeaways: Efficient coarse-to-fine pipeline: A two-stage reasoning pipeline that first processes low-resolution inputs to identify task-relevant regions and then re-encodes them at higher resolution, reducing computational cost while preserving essential information. Reward for reasoning-driven perception: […]

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models Read More +

ModelCat AI Announces AI Model Portability Across Silicon Devices

An industry first, ModelCat’s Agentic AI generates models for new chips using a user’s current production models, dramatically accelerating inferencing to the edge. SUNNYVALE, Calif., March 5, 2026 /PRNewswire/ — ModelCat, the creator of the world’s first fully autonomous AI model builder, today announced its latest innovative platform capability: Model Retargeting (Patent Pending). Using Model Retargeting, ModelCat customers gain model

ModelCat AI Announces AI Model Portability Across Silicon Devices Read More +

Why On-device AI Matters

This blog post was originally published at ENERZAi’s website. It is reprinted here with the permission of ENERZAi. Hello! I’m Minwoo Son from ENERZAi’s Business Development team. Through several posts so far, we’ve shared ENERZAi’s full-stack software capabilities for delivering high-performance on-device AI — including Optimium, our proprietary AI compiler that encapsulates our optimization expertise;

Why On-device AI Matters Read More +

Upcoming Webinar on LLM-driven Driver Development

On March 19, 2026, at 1:00 pm EDT (10:00 am PDT) Boston.AI will deliver a webinar “Intelligent Driver Development with LLM Context Engineering ” From the event page: Developing even simple sensor drivers can consume valuable engineering time, requiring manual transcription of registers from datasheets into code—an error-prone and repetitive process. In this webinar, you’ll

Upcoming Webinar on LLM-driven Driver Development Read More +

10xEngineers and Andes Enable High-Performance AI Compilation for RISC-V AX46MPV Cores

Hsinchu, Taiwan – February 26, 2026 – The collaboration between 10xEngineers, a services company specializing in AI compilers, and Andes Technology Corporation, a leading provider of high-performance, low-power 32- and 64-bit RISC-V processor IP and a Founding Premier Member of RISC-V International, delivers first-class AI workload compilation for Andes AX46MPV cores using 10xEngineers’ AI graph compiler, Baltoro. This collaboration enables

10xEngineers and Andes Enable High-Performance AI Compilation for RISC-V AX46MPV Cores Read More +

A Practical Guide to Recall, Precision, and NDCG

This blog post was originally published at Rapidflare’s website. It is reprinted here with the permission of Rapidflare. Introduction Retrieval-Augmented Generation (RAG) is revolutionizing how Large Language Models (LLMs) access and use information. By grounding models in domain specific data from authoritative sources, RAG systems deliver more accurate and context-aware answers. But a RAG system is

A Practical Guide to Recall, Precision, and NDCG Read More +

Google Adds “Agentic Vision” to Gemini 3 Flash

Jan. 30, 2026 — Google has announced Agentic Vision, a new capability in Gemini 3 Flash that turns image understanding into an active, tool-using workflow rather than a single “static glance.” Agentic Vision pairs visual reasoning with code execution (Python) so the model can iteratively zoom in, crop, annotate, and otherwise manipulate an image to

Google Adds “Agentic Vision” to Gemini 3 Flash Read More +

Robotics Builders Forum offers Hardware, Know-How and Networking to Developers

On February 25, 2026 from 8:30 am to 5:30 pm ET, Advantech, Qualcomm, Arrow, in partnership with D3 Embedded, Edge Impulse, and the Pittsburgh Robotics Network will present Robotics Builders Forum, an in-person conference for engineers and product teams. Qualcomm and D3 Embedded are members of the Edge AI and Vision Alliance, while Edge Impulse

Robotics Builders Forum offers Hardware, Know-How and Networking to Developers Read More +

On-Device LLMs in 2026: What Changed, What Matters, What’s Next

Editor’s note: Vikas Chandra is one of the keynote speakers for the 2026 Embedded Vision Summit. Check out his upcoming keynote “Scaling Down is the New Scaling Up here. The Embedded Vision Summit runs May 11-13, 2026 in Santa Clara, California. In On-Device LLMs: State of the Union, 2026, Vikas Chandra and Raghuraman Krishnamoorthi explain

On-Device LLMs in 2026: What Changed, What Matters, What’s Next Read More +

Getting Started with Edge AI on NVIDIA Jetson: LLMs, VLMs, and Foundation Models for Robotics

This article was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. Running advanced AI and computer vision workloads on small, power-efficient devices at the edge is a growing challenge. Robots, smart cameras, and autonomous machines need real-time intelligence to see, understand, and react without depending on the cloud. The NVIDIA

Getting Started with Edge AI on NVIDIA Jetson: LLMs, VLMs, and Foundation Models for Robotics 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.

Contact

Address

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

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