Computer Vision Research & Image Sensors

Imaging and sensing technologies play a crucial role in enabling the visualization and detection of objects, structures, or conditions that are not easily observable by the human eye or through conventional methods.

Our research focus is on optimizing computer vision in the areas of semiconductor design and fabrication, optimizing the image and sensing pipeline, and data protection and privacy. Our focus is on developing AI-driven solutions that not only complement but also augment the human sensing experience, ultimately expanding our ability to make sense of the complex world we inhabit.

Breakthroughs in Imaging & Sensing

Learn about our contributions to global AI research centered around groundbreaking advancements in computer vision and process innovation.

OUR WORK

Argus: A Compact and Versatile Foundation Model for Vision

While existing vision and multi-modal foundation model scan handle multiple computer vision tasks, they often suffer from significant limitations, including huge demand for data and computational resources during training and inconsistent performance across vision tasks at deployment time. To address these challenges, we introduce Argus1, a compact and versatile vision foundation model designed to support a wide range of vision tasks through a unified multitask architecture.

Learn More

OUR WORK

Schemato: An LLM for Netlist-to-Schematic Conversion

Our research explores a future in which AI-powered EDA unleashes innovation in multi-physics device technologies. We create machine learning models that incorporate scientific and engineering knowledge to enable optimal performance of design and fabrication processes.

Learn More

A person holds a camera close to the lens, focused against a warm, blurred sunset background

Vision and Sensing

Our research focuses on making camera systems faster and more secure by aligning AI models with specialized hardware. We study how to maximize energy efficiency and image quality while developing new ways to bake privacy protections directly into the sensing process.

AI for Chip Design

AI-driven EDA automates the design of analog circuits, digital systems, and microlenses. Integrating machine learning into the semiconductor pipeline accelerates hardware innovation while optimizing the end-to-end fabrication process.