computationalimaging.org
Automatic Integration
2 min · · David B. Lindell*, Julien N.P. Martel*, Gordon Wetzstein A new framework to integrate signals with implicit neural representations and its application to volume rendering. Numerical integration is a… · Shared by 6, including Matt Shaffer
openreview.net
Disagreement-Regularized Imitation Learning
· Method for addressing covariate shift in imitation learning using ensemble uncertainty · Shared by 5, including Matt Shaffer
AI Papers
Asymmetric self-play for automatic goal discovery in robotic manipulation
1 min · · We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play for goal discovery,… · Shared by 6, including Matt Shaffer
robotics-self-play.github.io
Robotics Asymmetric Self-Play
1 min · · We use asymmetric self-play to train a goal-conditioned policy for complex object manipulation tasks, and the learned policy can zero-shot generalize to many manually designed holdout tasks. · Shared by 7, including Matt Shaffer
AI Papers
Universal Off-Policy Evaluation
1 min · · When faced with sequential decision-making problems, it is often useful to be able to predict what would happen if decisions were made using a new policy. Those predictions must often be based on data… · Shared by 8, including AGI.Eth | MTL.Eth, Matt Shaffer
AI Papers
Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
1 min · · Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone. This requires a remarkable degree… · Shared by 4, including Matt Shaffer
AI Papers
Fine-Grained Few-Shot Classification with Feature Map Reconstruction Networks
· In this paper we reformulate few-shot classification as a reconstruction problem in latent space. The ability of the network to reconstruct a query feature map from support features of a given class… · Shared by 4, including Matt Shaffer
nex-mpi.github.io
NeX: Real-time View Synthesis with Neural Basis Expansion
1 min · · We present NeX, a new approach to novel view synthesis based on enhancements of multiplane image (MPI) that can reproduce NeXt-level view-dependent effects---in real time. · Shared by 18, including Alex J. Champandard 🌻, Alexander Seifert, Matt Shaffer, Lynn Cherny
github.com
mila-iqia/paperoni
· Search for scientific papers on the command line. Contribute to mila-iqia/paperoni development by creating an account on GitHub. · Shared by 5, including Matt Shaffer
AI Papers
A Survey on Deep Hashing Methods
1 min · · Nearest neighbor search is to find the data points in the database such that the distances from them to the query are the smallest, which is a fundamental problem in various domains, such as computer… · Shared by 4, including Matt Shaffer
AI Papers
Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
1 min · · We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to train with contrastive… · Shared by 4, including Matt Shaffer
AI Papers
Linformer: Self-Attention with Linear Complexity
· Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be… · Shared by 4, including Matt Shaffer
AI Papers
Flows for simultaneous manifold learning and density estimation
· We introduce manifold-learning flows (M-flows), a new class of generative models that simultaneously learn the data manifold as well as a tractable probability density on that manifold. Combining… · Shared by 4, including Matt Shaffer