Projects

Content Filters

Results

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

Addressing Challenges in Large-scale Distributed AI Systems

Adversarial Attacks Against Deep Reinforcement Learning Policies for Strategy Games

Agnostic Reinforcement Learning

Animating Animals from Video

Automatic Curriculum Generation and Emergent Complexity via Inter-agent Competition

Barcode Image Denoise - RL Approach

Building Ad-hoc Multi-agent System with Deep Reinforcement Learning

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

Differentiable Optimization for Game Theoretic Formulations

Dimensionality, Misspecification, and Wasserstein Projection

Disentangling Input Signals for Robust Computer Vision

Distributed Probabilistic Inference on Ray

Echo State Transformers

Efficient Object Detection with Super High-Resolution Image

Enabling Broader Learning Through Simplified and Personalized Summaries

Generalization Bounds for Interpolating Deep Neural Networks

Generalizing Domain Randomization for Zero-Shot Transfer

Generalizing Neural Radiance Fields

Graph Data Augmentation for Computer Systems

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 Non-Intuitive Physics in Children and Adults

Learning Robust Robot Policies to Manipulate and Fill Deformable Bags

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

Long-Horizon Decision-Making with Energy-Based Models

Low-Data Learning for Assistive Video Description

LP-based Algorithms for Reinforcement Learning

Mitigating Emergent Biases in Online Learning

Modeling Interpersonal Multimodal Signals in Social Conversation

Multi-agent Social Learning

Multi-task Learning with Safe and Differentiable Policies

Neural Program Synthesis from Diverse and Distant Context

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

Semantic Depth Extraction for Indoor Scenes

Smart Practice: Learning to Practice Skills from Demonstrations

Towards Robust Neural Networks with Conditional Generative Models

Towards Trustworthy Reinforcement Learning

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

Unsupervised Learning of Visual Context from Instance Segmentation

Using Deep Reinforcement Learning to Generalize Search in Games

Visual Locomotion: Synergistic Approach via Perception and Proprioception

X-Ray for Lateral Access Mechanical Search