Breakthrough optical processor lets AI compute at the speed of light

Science News from research organizations Breakthrough optical processor lets AI compute at the speed of light A blazing-fast optical engine uses light to supercharge AI decision-making. Date: October 28, 2025 Source: SPIE--International Society for Optics and Photonics Summary: Researchers at...

Science News from research organizations Breakthrough optical processor lets AI compute at the speed of light A blazing-fast optical engine uses light to supercharge AI decision-making. Date: October 28, 2025 Source: SPIE--International Society for Optics and Photonics Summary: Researchers at Tsinghua University developed the Optical Feature Extraction Engine (OFE2), an optical engine that processes data at 12.5 GHz using light rather than electricity. Its integrated diffraction and data preparation modules enable unprecedented speed and efficiency for AI tasks. Demonstrations in imaging and trading showed improved accuracy, lower latency, and reduced power demand. This innovation pushes optical computing toward real-world, high-performance AI. Share: Facebook Twitter Pinterest LinkedIN Email FULL STORY The proposed optical computing chip enables the high-speed, parallel processing for quantitative trading with unprecedented low latency, accelerating the crucial and demanding step of feature extraction. Credit: H. Chen, Tsinghua University Modern artificial intelligence (AI) systems, from robotic surgery to high-frequency trading, rely on processing streams of raw data in real time. Extracting important features quickly is critical, but conventional digital processors are hitting physical limits. Traditional electronics can no longer reduce latency or increase throughput enough to keep up with today's data-heavy applications. Turning to Light for Faster Computing Researchers are now looking to light as a solution. Optical computing -- using light instead of electricity to handle complex calculations -- offers a way to dramatically boost speed and efficiency. One promising approach involves optical diffraction operators, thin plate-like structures that perform mathematical operations as light passes through them. These systems can process many signals at once with low energy use. However, maintaining the stable, coherent light needed for such computations at speeds above 10 GHz has proven extremely difficult. To overcome this challenge, a team led by Professor Hongwei Chen at Tsinghua University in China developed a groundbreaking device known as the Optical Feature Extraction Engine, or OFE2. Their work, published in Advanced Photonics Nexus, demonstrates a new way to perform high-speed optical feature extraction suitable for multiple real-world applications. How OFE2 Prepares and Processes Data A key advance in OFE2 is its innovative data preparation module. Supplying fast, parallel optical signals to the core optical components without losing phase stability is one of the toughest problems in the field. Fiber-based systems often introduce unwanted phase fluctuations when splitting and delaying light. The Tsinghua team solved this by designing a fully integrated on-chip system with adjustable power splitters and precise delay lines. This setup converts serial data into several synchronized optical channels. In addition, an integrated phase array allows OFE2 to be easily reconfigured for different computational tasks. Once prepared, the optical signals pass through a diffraction operator that performs the feature extraction. This process is similar to a matrix-vector multiplication, where light waves interact to create focused "bright spots" at specific output points. By fine-tuning the phase of the input light, these spots can be directed toward chosen output ports, enabling OFE2 to capture subtle variations in the input data over time. Record-Breaking Optical Performance Operating at an impressive 12.5 GHz, OFE2 achieves a single matrix-vector multiplication in just 250.5 picoseconds -- the fastest known result for this type of optical computation. "We firmly believe this work provides a significant benchmark for advancing integrated optical diffraction computing to exceed a 10 GHz rate in real-world applications," says Chen. The research team tested OFE2 across multiple domains. In image processing, it successfully extracted edge features from visual data, creating paired "relief and engraving" maps that improved image classification and increased accuracy in tasks such as identifying organs in CT scans. Systems using OFE2 required fewer electronic parameters than standard AI models, proving that optical preprocessing can make hybrid AI networks both faster and more efficient. The team also applied OFE2 to digital trading, where it processed live market data to generate profitable buy and sell actions. After being trained with optimized strategies, OFE2 converted incoming price signals directly into trading decisions, achieving consistent returns. Because these calculations happen at the speed of light, traders could act on opportunities with almost no delay. Lighting the Way Toward the Future of AI Together, these achievements signal a major shift in computing. By moving the most demanding parts of AI processing from power-hungry electronic chips to lightning-fast photonic systems, technologies like OFE2 could usher in a new era of real-time, low-energy AI. "The advancements presented in our study push integrated diffraction operators to a higher rate, providing support for compute-intensive services in areas such as image recognition, assisted healthcare, and digital finance. We look forward to collaborating with partners who have data-intensive computational needs," concludes Chen. RELATED TOPICS Computers & Math Computers and Internet Robotics Computer Modeling Markets and Finance Artificial Intelligence Mobile Computing Computer Programming Distributed Computing RELATED TERMS Computing Robot Quantum computer Computing power everywhere Stock market Application software Scientific visualization Robot calibration Story Source: Materials provided by SPIE--International Society for Optics and Photonics. Note: Content may be edited for style and length. Journal Reference: Run Sun, Yuemin Li, Tingzhao Fu, Yuyao Huang, Wencan Liu, Zhenmin Du, Sigang Yang, Hongwei Chen. High-speed and low-latency optical feature extraction engine based on diffraction operators. Advanced Photonics Nexus, 2025; 4 (05) DOI: 10.1117/1.APN.4.5.056012 Cite This Page: MLA APA Chicago SPIE--International Society for Optics and Photonics. "Breakthrough optical processor lets AI compute at the speed of light." ScienceDaily. ScienceDaily, 28 October 2025. . SPIE--International Society for Optics and Photonics. (2025, October 28). Breakthrough optical processor lets AI compute at the speed of light. ScienceDaily. Retrieved July 13, 2026 from www.sciencedaily.com/releases/2025/10/251027224833.htm SPIE--International Society for Optics and Photonics. "Breakthrough optical processor lets AI compute at the speed of light." ScienceDaily. www.sciencedaily.com/releases/2025/10/251027224833.htm (accessed July 13, 2026). Explore More from ScienceDaily RELATED STORIES Logic With Light: Introducing Diffraction Casting, Optical-Based Parallel Computing Oct. 3, 2024 — Increasingly complex applications such as artificial intelligence require ever more powerful and power-hungry computers to run. Optical computing is a proposed solution to increase speed and power ... Hexagonal Electrohydraulic Modules Shape-Shift Into Versatile Robots Sep. 18, 2024 — Scientists at MPI-IS have developed electrically driven robotic components, called HEXEL modules, which can snap together into high-speed reconfigurable robots. Magnets embedded along the outside of ... Discovery Highlights 'Critical Oversight' in Perceived Security of Wireless Networks June 6, 2024 — A research team has uncovered an eavesdropping security vulnerability in high-frequency and high-speed wireless backhaul links, widely employed in critical applications such as 5G wireless cell phone ... Tapping Into the 300 GHz Band With an Innovative CMOS Transmitter Feb. 20, 2024 — New phased-array transmitter design overcomes common problems of CMOS technology in the 300 GHz band. Thanks to its remarkable area efficiency, low power consumption, and high data rate, the proposed ... Photonics-Based Wireless Link Breaks Speed Records for Data Transmission Feb. 1, 2024 — Researchers demonstrated a 300 GHz-band wireless link that was able to transmit data over a single channel at a rate of 240 gigabits per second. The wireless communication system employs signal ... Extracting the Best Flavor from Coffee May 9, 2023 — Researchers explore the role of uneven coffee extraction using a simple mathematical model. They split the coffee into two regions to examine whether uneven flow does in fact make weaker espresso. ... TRENDING AT SCITECHDAILY.com Astronomers Find a New Clue for Detecting Runaway Supermassive Black Holes Why You Hate Eating Bugs: DNA Reveals a 9,000-Year-Old Legacy Coffee May Protect the Liver in More Ways Than Scientists Realized The Hidden Health Risk of Sitting for Hours Without a Break

Source: ScienceDaily AI — Published October 28, 2025 at 13:14 UTC — Category: Research