A team led by Adityanarayanan Radhakrishnan at the Massachusetts Institute of Technology and Mikhail Belkin at the University of California San Diego has developed a method to hunt down and manipulate hidden concepts lurking inside large language models — the AI systems behind ChatGPT, Claude and their kin. Their approach, published this week in Science, can […]
In a pioneering breakthrough for artificial intelligence research, a team of scientists has unveiled a novel technique to precisely steer the output of large language models (LLMs) by manipulating specific internal concepts encoded within these models. This innovative approach promises significant advancements in making LLMs more reliable, efficient, and adaptable, while simultaneously shedding light on […]
A team of researchers has found a way to steer the output of large language models by manipulating specific concepts inside these models. The new method could lead to more reliable, more efficient, and less computationally expensive training of LLMs. But it also exposes potential vulnerabilities.
Will artificial intelligence ever be able to reason, learn and solve problems at levels comparable to humans? Four experts at the University of California San Diego believe the answer is yes, and that such artificial general intelligence has already arrived.
The 2026 IEEE Fellows Class acknowledges Vishnoi “for contributions to algorithms, optimization, and fairness in decision-making.”
Andrew Kahng is part of several major national initiatives that together are transforming how future engineers learn to design and build computer chips. His work is helping UC San Diego become a driving force in the nation’s growing semiconductor innovation ecosystem.
The rapid advancement of generative AI has brought remarkable innovations, from creating realistic images to generating human-like text. However, this power comes with significant responsibility. AI safety is crucial to ensure these systems are used ethically, fairly, and without unintended harm. Without proper safety measures, generative AI can spread misinformation, reinforce biases, or be exploited […]
An interview with Dr. Henrik Christensen, TILOS Robotics team co-lead and Distinguished Professor of Computer Science at UC San Diego, about the “marriage” of AI and physical automation. Christensen explains why the market’s fixation on sci-fi concepts has created a disconnect, leaving practical robotics companies poised for growth that is not yet priced in. The […]
This course covers the fundamentals of deep learning and the basics of deep neural networks, including different network architectures and optimization algorithms for training these networks, as well as applications to computer vision, robotics, and sequence modeling.
