Cornell Tech Develops Optical Receiver to Enhance AI Memory Management
- Published
- Source
- Spectrum.ieee.orgAutomaton
Cornell Tech researchers, led by Yifan He and Jae-sun Seo, have developed an innovative optical receiver that can modify its memory using light. This technology, presented at the IEEE/JSAP Symposium, aims to alleviate the memory demands of AI systems, potentially reducing energy consumption in data centers and AI-powered robots.
The significance of this advancement lies in its ability to facilitate high-bandwidth data transfer with lower energy loss compared to traditional metal connections. By utilizing a QR code-like optical matrix, the receiver can adjust AI model parameters without relying on power-intensive analog circuits, addressing a major bottleneck in current AI chip designs.
Looking ahead, the researchers are focused on creating a rapid optical transmitter capable of altering light matrices millions of times per second. While commercialization is still a challenge due to the size of the photosensitive cells, the potential applications in robotics and edge computing are promising, particularly in AI-driven warehouses and factories.
Original report
Optical Tech Would Update a Robot’s AI on the Fly
Spectrum.ieee.orgAutomaton · Alex MusicThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
-
12
RobotToday Weekly October 12 – 16, 2026 RobotToday · 1 week ago
Related Suppliers
Hunan Chiopt Optical Technology Co., Ltd. 湖南长步道光电科技股份有限公司
China
Changsha, China lensmaker (registered as Hunan Changbudao Optoelectronic Technology) founded 2010; builds machine-vision and telecentric lenses.
ImmerVision
Canada
ImmerVision develops wide-angle and panomorph lens technology and image processing software for 360-degree cameras used in automotive, security, and robotics.
Acheron Labs
Austria
Vienna-based robotics software startup building an LLM-driven control layer that lets Unitree's G1 humanoid and Go2 quadruped follow spoken commands.
MemryX
United States
US AI chip startup co-founded 2019 at University of Michigan, developing edge AI accelerator chips with at-memory dataflow for robotics, vision, and video.
DeepCtrls 深度智控
China
Nanjing energy-AI startup founded in 2018 by Tsinghua/Berkeley Lab alumni; its IoT platform targets at least 10% facility energy savings.
Q-Bot Limited
United Kingdom
London firm whose robots spray about 12 cm of insulation foam under suspended timber floors, with over 5,500 UK homes treated.
inOrbit
United States
Mountain View robot orchestration SaaS founded 2017; $10M Series A Sep 2025; multi-vendor fleet management across 4 continents in warehouses and factories.
Tutor Intelligence
United States
MIT CSAIL spinout delivering AI-powered robot workers for manufacturing and logistics via RaaS, with Cassie palletizer and Sonny humanoid platforms.
Fibertek, Inc.
United States
US laser and lidar developer founded in 1983, supplying advanced photonics systems to NASA and the US Department of Defense.
ARK Electronics
United States
Salt Lake City firm founded 2018 that builds US-made, NDAA-compliant drone flight controllers, GPS and sensors, several listed on Blue UAS.
SolverX
Korea, Republic of (South)
South Korean AI-aided engineering startup that accelerates CAE simulation workflows using physics-informed AI models across automotive, aerospace, and.
Striding.AI
Striding.AI (Striding AI) is a Beijing-based embodied-AI and robotics company founded in early 2026. It is led by founder and CEO Yao Song; co-founder Yu Chao works on reinforcement-learning post-training, and co-founder Yang Yuxin was named President for global expansion in September 2026. Funding is reported at nearly 100 million USD in total, with the latest angel round announced in June 2026 and investors including Charoen Pokphand Group, Huaqin Technology, and Jiuan Medical. The product line includes H1, a bipedal humanoid service robot; C1, a wheeled dual-arm restocking and transport robot; A1, a planned compact robot for high-precision handling of delicate items such as checkout tasks; and M1, a fleet platform for robot lifecycle management, orchestration, and optimization. On the software side it has developed SLM-0.5, a latent-space world action model with 2.3 billion parameters, the STEAM post-training system based on reinforcement learning, and the Rpent embodied agent framework. H1, C1, M1, and SLM-0.5 were launched in October 2026, and commercial service is planned for 2027. The company has said it will start with retail deployments such as shelf restocking and inventory counting.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
