UC San Diego Today

A New Method to Steer AI Output Uncovers Vulnerabilities and Potential Improvements

A team of researchers has found a way to steer the output of large language models by manipulating specific concepts inside ...
IEEE

Autonomous Vehicle Path Tracking: Stochastic Tube Model Predictive Control With Covariance Steering and Discounted Chance Constraints

Abstract: The path tracking performance of autonomous vehicles degrades due to model uncertainties and external disturbances. Tube-based Model Predictive Control (MPC) has been regarded as an ...
GitHub

Fara-7B: An Efficient Agentic Model for Computer Use

Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that ...
IEEE

Step Size Adaptation for Accelerated Stochastic Momentum Algorithm Using SDE Modeling and Lyapunov Drift Minimization

Abstract: Training machine learning models often involves solving high-dimensional stochastic optimization problems, where stochastic gradient-based algorithms are hindered by slow convergence.