55 citations · 283 across the 50 of their papers we have counts for
9 papers · 1 filter
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…
Regularized Training of Nearest Neighbor Language Models
Jean-Francois Ton, Walter Talbott, Shuangfei Zhai +1
Including memory banks in a natural language processing architecture increases model capacity by equipping it with additional data at inference time. In this paper, we build upon $…
Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
Shih-Yu Sun, Vimal Thilak, Etai Littwin +2
Deep linear networks trained with gradient descent yield low rank solutions, as is typically studied in matrix factorization. In this paper, we take a step further and analyze impl…
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
Etai Littwin, Omid Saremi, Shuangfei Zhai +4
We analyze the learning dynamics of infinitely wide neural networks with a finite sized bottle-neck. Unlike the neural tangent kernel limit, a bottleneck in an otherwise infinite w…
Fast and Explicit Neural View Synthesis
Pengsheng Guo, Miguel Angel Bautista, Alex Colburn +4
We study the problem of novel view synthesis from sparse source observations of a scene comprised of 3D objects. We propose a simple yet effective approach that is neither continuo…
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…
MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
Chen Huang, Shuangfei Zhai, Pengsheng Guo +1
We study the problem of directly optimizing arbitrary non-differentiable task evaluation metrics such as misclassification rate and recall. Our method, named MetricOpt, operates in…
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…