research
∙
01/20/2023
Neural Architecture Search: Insights from 1000 Papers
In the past decade, advances in deep learning have resulted in breakthro...
share
research
∙
10/17/2022
What Makes Convolutional Models Great on Long Sequence Modeling?
Convolutional models have been widely used in multiple domains. However,...
research
∙
01/29/2022
AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models
Knowledge distillation (KD) methods compress large models into smaller s...
research
∙
06/18/2020
Reparameterized Variational Divergence Minimization for Stable Imitation
While recent state-of-the-art results for adversarial imitation-learning...
research
∙
05/19/2020
A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks
Many high-level procedural tasks can be decomposed into sequences of ins...
research
∙
05/31/2019
Efficient Forward Architecture Search
We propose a neural architecture search (NAS) algorithm, Petridish, to i...
research
∙
05/12/2019
Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations
Assemblies of modular subsystems are being pressed into service to perfo...
research
∙
12/10/2018
Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention
We present Vision-based Navigation with Language-based Assistance (VNLA)...
research
∙
06/27/2018
Learn-to-Score: Efficient 3D Scene Exploration by Predicting View Utility
Camera equipped drones are nowadays being used to explore large scenes a...
research
∙
05/23/2018
Discovering Blind Spots in Reinforcement Learning
Agents trained in simulation may make errors in the real world due to mi...
research
∙
11/17/2017
Data-driven Planning via Imitation Learning
Robot planning is the process of selecting a sequence of actions that op...
research
∙
10/30/2017
Log-DenseNet: How to Sparsify a DenseNet
Skip connections are increasingly utilized by deep neural networks to im...
research
∙
08/22/2017
Anytime Neural Network: a Versatile Trade-off Between Computation and Accuracy
Anytime predictors first produce crude results quickly, and then continu...
research
∙
05/15/2017
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
Developing and testing algorithms for autonomous vehicles in real world ...
research
∙
12/01/2016
Flight Dynamics-based Recovery of a UAV Trajectory using Ground Cameras
We propose a new method to estimate the 6-dof trajectory of a flying obj...
research
∙
11/13/2016
Learning to Gather Information via Imitation
The budgeted information gathering problem - where a robot with a fixed ...
research
∙
10/17/2016
Risk-Aware Algorithms for Adversarial Contextual Bandits
In this work we consider adversarial contextual bandits with risk constr...
research
∙
11/24/2014
Vision and Learning for Deliberative Monocular Cluttered Flight
Cameras provide a rich source of information while being passive, cheap ...
research
∙
05/11/2013
Learning Policies for Contextual Submodular Prediction
Many prediction domains, such as ad placement, recommendation, trajector...
research
∙
11/07/2012
Learning Monocular Reactive UAV Control in Cluttered Natural Environments
Autonomous navigation for large Unmanned Aerial Vehicles (UAVs) is fairl...
research
∙
02/09/2012
