VASC Seminar
Jia-Bin Huang
Capital One-endowed Associate Professor
University of Maryland College Park

Controllable Visual Imagination

3305 Newell-Simon Hall

Abstract: Generative models have empowered human creators to visualize their imaginations without artistic skills and labor. A prominent example is large-scale text-to-image generation models. However, these models often are difficult to control and do not respect 3D perspective geometry and temporal consistency of videos. In this talk, I will showcase several of our recent efforts to [...]

RI Seminar
Alfred Rizzi
Chief Technology Officer
RAI Institute

Developing Physically Capable and Intelligent Robots

1403 Tepper School Building

Abstract: Dr. Rizzi will provide an overview of the ongoing work at the Robotics and AI Institute (RAI Institute) and its ongoing research efforts focused on the design and control of the next generation of intelligent and capable robotics systems. The focus is on the development of systems capable of performing complex dynamic tasks at [...]

VASC Seminar
Niv Cohen
Research Scientist
New York University

Discovering and Erasing Undesired Concepts

3305 Newell-Simon Hall

Abstract: The rapid growth of generative models allows an ever-increasing variety of capabilities. Yet, these models may also produce undesired content such as unsafe or misleading images, private information, or copyrighted material. In this talk, I will discuss practical methods to prevent undesired generations. First, I will show how the challenge of avoiding undesired generations [...]

RI Seminar
Ken Goldberg
Professor
Electrical Engineering & Computer Sciences, University of California, Berkeley

Is Data All You Need?: Large Robot Action Models and Good Old Fashioned Engineering

1403 Tepper School Building

Abstract: Enthusiasm has been skyrocketing for humanoids based on recent advances in "end-to-end" large robot action models. Initial results are promising, and several collaborative efforts are underway to collect the needed demonstration data. But is data really all you need? Although end-to-end Large Vision, Language, Action (VLA) Models have potential to generalize and reliably solve [...]

RI Seminar
Nima Fazeli
Assistant Professor
Robotics and Mechanical Engineering, University of Michigan

RI Seminar with Nima Fazeli

1403 Tepper School Building

RI Seminar
Nikolay Atanasov
Associate Professor
Electrical and Computer Engineering, University of California, San Diego

RI Seminar with Nikolay Atanasov

1403 Tepper School Building

RI Seminar
Sangbae Kim
Professor
Mechanical Engineering, Massachusetts Institute of Technology

Physical Intelligence and Cognitive Biases Toward AI

1403 Tepper School Building

Abstract: When will robots be able to clean my house, dishes, and take care of laundry? While we source labor primarily from automated machines in factories, the penetration of physical robots in our daily lives has been slow. What are the challenges in realizing these intelligent machines capable of human level skill? Isn’t AI advanced [...]

RI Seminar
Charlie Kemp
Chief Technology Officer
Hello Robot Inc.

RI Seminar with Charlie Kemp

1403 Tepper School Building