Unleash AI Performance with Revolutionary 3D X-DRAM and X-HBM Technologies
Date: Sept 4, Thursday, 2025
Time: 6:00pm – 7pm Network
7pm -8:30pm Presentation
Avenue: 2880 Zanker Road, Suite 103, San Jose, CA 95134 (ITRI)
Subject: Unleash AI Performance with Revolutionary 3D X-DRAM and X-HBM Technologies
Speaker: Andy Hsu and Ray Tsay, NEO Semiconductor
Andy Hsu is the Founder and CEO of NEO Semiconductor. He has more than 25 years of experience in the semiconductor and memory industry, an Andy has more than 120 granted U.S. patents. He majored at Neural Networks and Artificial Intelligence (AI) for a master’s degree in Electrical, Computer, and System Engineering (ECSE) from Rensselaer Polytechnic Institute (RPI) in New York. He earned a bachelor’s degree from the National Cheng-Kung University in Taiwan.
Ray Tsay is the Co-Founder & VP of Engineering of NEO Semiconductor. Ray has over 30 years of experience in the semiconductor industry. Prior to NEO, he worked at many companies including Integrated Silicon Solution (ISSI), ICT, and EG&G Reticon. He has broad experience in various products such as CCD, CPLD, SRAM, EEPROM, EPROM, and flash memory. He holds a MS degree in Electrical and Computer Engineering from Arizona State University, a MS in Chemical and Material Engineering from the University of Iowa, and a BS in Chemical Engineering from National Central University in Taiwan.
Abstract
AI chip performance is fundamentally constrained by memory capacity and bandwidth—a challenge known as the “memory wall.” Current AI architectures based on traditional DRAM and HBM technologies struggle to scale beyond 64 GB capacity and a 4096-bit bus width, which is insufficient for the growing demands of next-generation AI workloads.
To address this limitation, a game-changing 3D X-DRAM technology has been invented, leveraging a 3D NAND-like cell structure to achieve exceptionally high density. These 3D array cells can be manufactured using a modified process derived from the mature 3D NAND flash process, enabling a 10× increase in DRAM capacity while significantly reducing development complexity and costs.
Furthermore, 3D X-DRAM enables a new class of extremely high bandwidth memory, called X-HBM. By eliminating TSVs (through-silicon via) and using advanced hybrid bonding technology, X-HBM delivers a 16× increase in bandwidth while substantially lowering power consumption and heat generation. This breakthrough represents a transformative innovation for AI applications, unlocking unprecedented performance and efficiency.
魅麗、迷人、惘然─歐洲寫實主義的愛情小說
理性、知性、感性為人生三大認知：其中感性有愛情、宗教及文學。長篇小說最重要的主題是戰爭與愛情 - 愛情是一種感覺。夏教授將談到羅曼史Romance 產生背景；浪漫主義及寫實主義的愛情小說；中國及西方愛情觀及婚姻觀不同；歐洲及美國愛情小說概述；聖經中為何沒有愛情?夏教授將介紹代表性的至少七部近代歐洲愛情小說：包括《咆嘯山莊》《安娜卡列尼娜》《查泰萊夫人的情人》《齊瓦哥醫生》等。
Physical AI: The Next Wave of Artificial Intelligence
Talk Title: “Physical AI: The Next Wave of Artificial Intelligence” by Dr. William Kao
Date: Wedn Sept 10, 2025 6:30 - 8:30 PM, at ITRI 2880 Zanker Suite 103. Seminar talk will start at 7PM.
The Zoom link for the seminar is as follows:
Join Zoom Meeting
https://us02web.zoom.us/j/82746765328
Meeting ID: 827 4676 5328
Seminar Talk: “Physical AI: The Next Wave of Artificial Intelligence” by Dr. William Kao
Abstract: At this year’s GPU Technical Conference (March 17, 2025) Nvidia’s CEO Jensen Huang introduced the concept of Physical AI.
Artificial Intelligence has been evolving from Perception AI (e.g., image and speech recognition), through Generative AI (e.g., text and image synthesis), and Agentic AI (e.g., task planning and decision-making), to the next frontier of Physical AI, where intelligent systems are embodied in robots that combine perception, generation, and agency to act and adapt in the real world. Physical AI understands the laws of physics and can autonomously perform complex tasks in the real world.
Physical AI represents a powerful convergence of AI algorithms, robotics, sensor technologies, and real-time control systems. It represents a significant leap from purely digital AI models to embodied intelligence, where cognition and action are seamlessly integrated.
In this talk Dr. Kao will present an overview of Physical AI, its architecture, characteristics, components and how it works. He will discuss PAI practical applications across sectors such as healthcare (assistive robots), manufacturing (intelligent automation), logistics (warehouse robotics), and personal services (home assistants).
Finally, he will explore what the future holds for Physical AI. Could it be the bridge to Artificial General Intelligence (AGI), where machines not only think, but also act with purpose in the real world?
Speaker Bio:
Dr. William Kao received his BSEE, MSEE and PhD from the University of Illinois Urbana-Champaign. He worked in the Semiconductor and Electronic Design Automation industries for more than 30 years holding several senior and Executive engineering management positions at Texas Instruments, Xerox Corporation, and Cadence Design Systems.
Dr. Kao has authored more than 40 technical papers on IC CAD at IEEE Journals and Conferences and holds eight US software and IC design patents. He was an Adjunct Professor at UCLA Electrical Engineering Department where he taught courses in computer aided IC design.
Dr. Kao is a Senior Member of IEEE and was one of the founding members of IEEE-Circuits and Systems - Silicon Valley Chapter.
Dr. Kao teaches Clean Technology and Emerging Technology courses at the University of California Santa Cruz, Silicon Valley Extension.
He has given more than 100 technical seminars on various Emerging Technologies including Clean Technology, Renewable Energy, Big Data and Data Analytics, IoT, Smart Cities, Augmented and Virtual Reality, Robotics, Drones, AI / Machine Learning, Robotics, 5G, 3D Printing, the Metaverse and Satellite Communications.