VASC Seminar
Michael Zollhoefer
Research Scientist
Reality Labs Research

Complete Codec Telepresence

Newell-Simon Hall 3305

Abstract:  Imagine two people, each of them within their own home, being able to communicate and interact virtually with each other as if they are both present in the same shared physical space. Enabling such an experience, i.e., building a telepresence system that is indistinguishable from reality, is one of the goals of Reality Labs [...]

VASC Seminar
Kayvon Fatahalian
Associate Professor of Computer Science
Stanford University

R.I.P ohyay: experiences building online virtual experiences during the pandemic: what works, what hasn’t, and what we need in the future

Newell-Simon Hall 3305

Abstract:  During the pandemic I helped design ohyay (https://ohyay.co), a creative tool for making and hosting highly customized video-based virtual events. Since Fall 2020 I have personally designed many online events: ranging from classroom activities (lectures, small group work, poster sessions, technical papers PC meetings), to conferences, to virtual offices, to holiday parties involving 100's [...]

VASC Seminar
Fabio Pizzati
PhD student
Inria

Physics-informed image translation

Abstract:  Generative Adversarial Networks (GANs) have shown remarkable performances in image translation, being able to map source input images to target domains (e.g. from male to female, day to night, etc.). However, their performances may be limited by insufficient supervision, which may be challenging to obtain. In this talk, I will present our recent works [...]

RI Seminar
Chelsea Finn
Assistant Professor
Computer Science & Electrical Engineering, Stanford University

Robots Should Reduce, Reuse, and Recycle

1305 Newell Simon Hall

Abstract: Despite numerous successes in deep robotic learning over the past decade, the generalization and versatility of robots across environments and tasks has remained a major challenge. This is because much of reinforcement and imitation learning research trains agents from scratch in a single or a few environments, training special-purpose policies from special-purpose datasets. In [...]

VASC Seminar
Adriana Kovashka
Associate Professor in Computer Science
University of Pittsburgh

Weak Multi-modal Supervision for Object Detection and Persuasive Media

Newell-Simon Hall 3305

Abstract:  The diversity of visual content available on the web presents new challenges and opportunities for computer vision models. In this talk, I present our work on learning object detection models from potentially noisy multi-modal data, retrieving complementary content across modalities, transferring reasoning models across dataset boundaries, and recognizing objects in non-photorealistic media.  While the [...]

RI Seminar
Byron Boots
Amazon Professor
Machine Learning in the Paul G. Allen School of Computer Science, University of Washington

Machine Learning and Model Predictive Control for Adaptive Robotic Systems

1305 Newell Simon Hall

Abstract: In this talk I will discuss several different ways in which ideas from machine learning and model predictive control (MPC) can be combined to build intelligent, adaptive robotic systems. I’ll begin by showing how to learn models for MPC that perform well on a given control task. Next, I’ll introduce an online learning perspective on [...]

Field Robotics Center Seminar
José Luís Silva
Assistant Professor
Science and Technology Department, University Institute of Lisbon

Towards more effective remote execution of exploration operations using multimodal interfaces

1305 Newell Simon Hall

Abstract: Remote robots enable humans to explore and interact with environments while keeping them safe from existing harsh conditions (e.g., in search and rescue, deep sea or planetary exploration scenarios). However, the gap between the control station and the remote robot presents several challenges (e.g., situation awareness, cognitive load, perception, latency) for effective teleoperation. Multimodal [...]

VASC Seminar
Andrew Owens
Assistant Professor
Electrical Engineering & Computer Science , University of Michigan

Learning Visual, Audio, and Cross-Modal Correspondences

Newell-Simon Hall 3305

Abstract:  Today's machine perception systems rely heavily on supervision provided by humans, such as labels and natural language. I will talk about our efforts to make systems that, instead, learn from two ubiquitous sources of unlabeled data: visual motion and cross-modal sensory associations. I will begin by discussing our work on creating unified models for [...]

VASC Seminar
Lachlan MacDonald
Postdoc
Australian Institute for Machine Learning, University of Adelaide

Towards a formal theory of deep optimisation

Newell-Simon Hall 3305

Abstract:  Precise understanding of the training of deep neural networks is largely restricted to architectures such as MLPs and cost functions such as the square cost, which is insufficient to cover many practical settings.  In this talk, I will argue for the necessity of a formal theory of deep optimisation.  I will describe such a [...]