A global team of researchers led by Ludmil Alexandrov, a professor of bioengineering and cellular and molecular medicine, has been selected by Cancer Grand Challenges to receive up to $25M to better understand how cancer begins. Alexandrov and collaborators across the United States, the Netherlands and the United Kingdom will work to decode mutational signatures, which are the DNA “fingerprints” that reveal the causes of cancer development. Their work builds on efforts to better understand early-onset colorectal cancer, lung cancer in never-smokers and more. With the new funding, the team aims to advance fundamental understanding and translate insights into better solutions for cancer prevention, detection and therapy. 

Drawing inspiration from the brain, electrical engineers have developed a hardware platform that could lead to compact, low-power AI hardware. The platform mimics how the brain processes information by combining memory and computation on the same chip — and allowing its components to interact collectively like neurons in the brain. The brain-inspired platform improved the speed, accuracy and energy efficiency of pattern recognition in two simulated tasks: recognizing spoken digits and detecting epileptic seizures early from brain-wave recordings.

Computer scientists and weather scientists have taken the first steps toward creating an AI agent capable of analyzing and answering questions in natural language, such as English, about data from AI-driven weather forecasting models.The tool could help democratize earth science, making it easier for students and young scientists to interact with different datasets. The researchers also hope the findings will lead to AI agents that bring similar advances to other disciplines, especially climate science.

A scalable, automated grading system designed to provide students with intelligent feedback on their work while freeing up instructor time for in-person student support was recognized with the Jacobs School’s inaugural Award for Outstanding Teaching Innovation. This new award complements the School’s existing Best Undergraduate Teacher, Best Graduate Mentor, and Outstanding Faculty Mentor awards that recognize our talented and creative educators. 

Researchers found a way to steer the output of large language models by manipulating specific concepts inside these models. The work, published in Science, could lead to more reliable, more efficient, and less computationally expensive training of LLMs. But it also exposes potential vulnerabilities — the researchers found that their method could get an LLM to operate outside of its guardrails, a practice known as jailbreaking. The work was led by computer scientists and data scientists at UC San Diego and MIT. 

Jacobs School of Engineering faculty Abdoulaye Ndao (electrical and computer engineering), Kenneth Vecchio (chemical and nano engineering) and Edward Wang (electrical and computer engineering and the Design Lab) have been named Senior Members of the National Academy of Inventors in recognition of their outstanding achievements in innovation. Ndao was recognized for optical technologies that can sense and image biological molecules; Vecchio was recognized for computational tools that can rapidly identify commercial candidates for advanced metal and ceramic materials; and Wang was recognized for transforming ordinary smartphones into powerful health monitoring tools.

Structural engineers are making railroad track inspection more effective, thanks to advances in ultrasound. The researchers applied an innovative form of ultrasound with new beamforming algorithms to create a device that can be embedded in the wheel of a cart — and one day, potentially a train itself — to inspect each and every mile of rail for defects and internal cracks not visible to the naked eye. The device provides real-time high-resolution images of any internal defects as the cart is pushed over a railroad track.

Researchers and clinicians from across the country developed a new AI model of the male urinary tract that could make prostate cancer radiation therapy more precise and help reduce side effects, such as urinary complications. The work was led by Yuze Song, an electrical engineering doctoral student at the Jacobs School of Engineering, alongside Dr. Tyler Seibert, an associate professor of radiation medicine and applied sciences at UC San Diego School of Medicine and radiation oncologist at UC San Diego Health.

Connect with the Jacobs School