Projects

Content Filters

Results

Adding Safety and Robustness to Learning for Robots by Learning on Robots

Addressing Challenges in Large-scale Distributed AI Systems

Animating Animals from Video

Automatic Curriculum Generation and Emergent Complexity via Inter-agent Competition

Combining Causal Reasoning and Information Theory to Empower Humans through Human-Agent Collaboration

Compressing High Capacity Models with Implicit Neural Networks and Frank-Wolfe

Control of Microrobots with Data and Computationally Efficient Reinforcement Learning

Dimension-free Statistical and Computational Guarantee for Optimal Transport

Generalizing Domain Randomization for Zero-Shot Transfer

Grounded and Modular Vision and Language Learning

Hardware Software Co-Design for NLP and Recommendation Systems

Interactive Learning from Vision and Touch

Investigations into the Complexity of Nonconvex Optimization

Large-scale 3D Reconstruction from Multi-view Image Datasets

Learning Space Partitions for Path Planning

Learning to Collaborate with Human Players

Learning-based Safe Navigation for Dynamic Legged Robots

Local Parametric Learning Rules for Parallel and Scalable Training

Long Term Video Understanding

Low-Data Learning for Assistive Video Description

Modeling Interpersonal Multimodal Signals in Social Conversation

Multi-agent Social Learning

Never Decrypt Data Lake

NumS: NumPy API-Compatible Framework backed by Ray

Offline Recovery RL: Offline Reinforcement Learning with Safe Online Adaptation

On Theoretical Foundations for Transfer Learning

Optimal Data Augmentation Strategy Search

Robustness for Deep Learning/Ethical AI Through Human Value Modeling

Safe and Sound: Learning Locomotion Skills Across Robot Morphology

Safe Robotic Learning Via Reachability Theory

Self-supervised Learning for Generic Visual Representation

Smart Practice: Learning to Practice Skills from Demonstrations

Towards Robust Neural Networks with Conditional Generative Models

Training Sparse High Capacity Models with Implicit Neural Networks and Frank-Wolfe

Uncertainty Aware Machine Learning for Model Based Planning and Control

Universal Representation Learning for Control

Using Deep Reinforcement Learning to Generalize Search in Games

X-Ray for Lateral Access Mechanical Search