6.7k citations · 8.6k across the 13 of their papers we have counts for
15 papers
Suprathermal population associated with stream interaction regions observed by STEREO-A: New insights
Bijoy Dalal, Dibyendu Chakrabarty, Nandita Srivastava +1
Stream interaction regions (SIRs) are often thought to be responsible for the generation of suprathermal population in the interplanetary medium. Despite the source being same, wid…
Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation
Martin Bertran, Walter Talbott, Nitish Srivastava +1
Learning generalizeable policies from visual input in the presence of visual distractions is a challenging problem in reinforcement learning. Recently, there has been renewed inter…
Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models
Nitish Srivastava, Walter Talbott, Martin Bertran Lopez +2
Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space. However, learning world models in unconstrained environ…
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Yue Wu, Shuangfei Zhai, Nitish Srivastava +4
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and ac…
An Attention Free Transformer
Shuangfei Zhai, Walter Talbott, Nitish Srivastava +4
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are…
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
Terrance DeVries, Miguel Angel Bautista, Nitish Srivastava +2
We tackle the challenge of learning a distribution over complex, realistic, indoor scenes. In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose sc…
On the generalization of learning-based 3D reconstruction
Miguel Angel Bautista, Walter Talbott, Shuangfei Zhai +2
State-of-the-art learning-based monocular 3D reconstruction methods learn priors over object categories on the training set, and as a result struggle to achieve reasonable generali…
Capsules with Inverted Dot-Product Attention Routing
Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh +1
We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote. T…
Geometric Capsule Autoencoders for 3D Point Clouds
Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov
We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric…
Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
Elman Mansimov, Nitish Srivastava, Ruslan Salakhutdinov
We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training Spatio-Te…
Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
Shengxin Zha, Florian Luisier, Walter Andrews +2
We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study…
Unsupervised Learning of Video Representations using LSTMs
Nitish Srivastava, Elman Mansimov, Ruslan Salakhutdinov
We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length re…
Learning Generative Models with Visual Attention
Yichuan Tang, Nitish Srivastava, Ruslan Salakhutdinov
Attention has long been proposed by psychologists as important for effectively dealing with the enormous sensory stimulus available in the neocortex. Inspired by the visual attenti…
Modeling Documents with Deep Boltzmann Machines
Nitish Srivastava, Ruslan R Salakhutdinov, Geoffrey E. Hinton
We introduce a Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents. We overcome the…
Improving neural networks by preventing co-adaptation of feature detectors
Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky +2
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly om…