01:09:25

RobotLearning: Scaling Behavoir Cloning

51:10

RobotLearning: Scaling Behavior Cloning Part2

38:35

RobotLearningIntroPart2

01:49:46

Robot Learning 2025: Foundational Models for Robotics and Scaling DeepRL

53:50

Vincent Leroy: From CroCo to MASt3R: A Paradigm Change in 3D Vision

01:26:56

Coding Generalist Robotics Policies

04:58

Improving Intrinsic Exploration by Creating Stationary Objectives | ICLR 2024

01:38:45

Foundational Models for Robot Control

48:17

Mengdi Xu: Building Adaptable Generalist Robots

04:54

One-4-All: Neural Potential Fields for Embodied Navigation

57:37

Karl Schmeckpeper: Robots learning like humans

57:47

Liyiming Ke: Data-Driven Fine Manipulation: Pushing Boundaries in Robotic Precision

01:10:36

Yevgen Chebotar: RT-2- Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

01:02:17

Dhruv Shah: A General-Purpose Robotic Navigation Model

02:06:19

How to write better than ChatGPT part 1: Sentence Structure

01:57:26

How to Write Better than ChatGPT Part 3: Organization and Collaboration

02:02:12

How to Write Better than ChatGPT Part 2: Paragraphs and staying on topic

05:03

Towards Learning to Imitate from a Single Video Demonstration

45:38

Developing Robots that Autonomously Learn and Plan in the Real World

02:02:48

IROS 2021 Workshop on the Broader Impacts of Self-Driving Cars

04:06

The Mimosa Manifesto

05:21

Fairness and Friends

05:12

Convolution Can Incur Foveation Effects

04:55

Interactive Media for Understanding ML Methods: A Case-Study on Graph Neural Networks

01:22:33

Chao Qu - Depth completion via deep basis fitting

18:34

Jung Hee Kim - Differentiable HDR image synthesis

27:54

Ming Lin - Differentiable physics for learning and control

01:38:40

Peter Battaglia - Exploiting differentiability for learning and prediction

06:12

Q&A: Georgia Gkioxari

01:23:49

Dan Biderman - Inverse articulated body dynamics from video

01:34:12

Andrea Tagliasacchi - One representation to rule them all

01:03:29

Panel discussion - The promises and perils of differentiable methods

06:00

Q&A: Peter Battaglia

21:17

Nils Thuerey - Phiflow: A differentiable PDE solving framework for deep learning

01:45:57

Yuanming Hu - Physical simulation and AI: Differentiability

25:17

Georgia Gkioxari - Reasoning about scenes and objects

12:05

Q&A: Yuanming Hu

01:33:35

Bethany Lusch - Data-driven discovery of coordinates and equations

20:25

Paula Gradu - DELUCA: Differentiable control library

07:09

Opening remarks

08:42

Q&A: Contributed talks

04:08

Q&A: Camillo Jose Taylor

17:10

Zijun Cui - Blendshape-augmented facial action units detection

05:54

Q&A: Bethany Lusch

35:03

Sanja Fidler: AI for 3D content creation

01:03:04

Master's student Gunshi Gupta presenting "La-MAML: Look-ahead Meta Learning for Continual Learning"

40:16

Transfer-Aware Kernels, Priors and Latent Spaces from Sim to Real

04:50

On Assessing the Value of Simulation for Robotics

01:16:45

Stefanie Tellex - Towards Complex Language in Partially Observed Environments