sarafridov.github.io
K-Plane
· Abstract: We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions. Our model uses d-choose-2 planes to represent a d-dimensional scene, providing a seamless way to go from… · Shared by 6, including Matt Shaffer
AI Papers
Training Neural Networks with Fixed Sparse Masks
1 min · · During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of… · Shared by 4, including Matt Shaffer
AI Papers
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
1 min · · A long-term goal of reinforcement learning is to design agents that can autonomously interact and learn in the world. A critical challenge to such autonomy is the presence of irreversible states which… · Shared by 4, including Matt Shaffer
AI Papers
ARMOR: A Model-based Framework for Improving Arbitrary Baseline Policies with Offline Data
1 min · · We propose a new model-based offline RL framework, called Adversarial Models for Offline Reinforcement Learning (ARMOR), which can robustly learn policies to improve upon an arbitrary baseline policy… · Shared by 5, including Matt Shaffer
agarwl.github.io
Beyond Tabula Rasa: Reincarnating Reinforcement Learning
· This work argues for an alternative approach to RL research, where we build on prior computational work, which we believe could significantly improve real-world RL adoption and help democratize it… · Shared by 6, including Matt Shaffer
zju3dv.github.io
NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing
1 min · · Very recently neural implicit rendering techniques have been rapidly evolved and shown great advantages in novel view synthesis and 3D scene reconstruction. However, existing neural rendering methods… · Shared by 5, including Matt Shaffer
accelagent.github.io
Evolving Curricula
17+ min · · Interactive publication for the paper "Evolving Curricula with Regret-Based Environment Design." · Shared by 8, including Matt Shaffer
sites.google.com
Making Sense of Vision and Touch
2 min · · Michelle A. Lee*, Yuke Zhu*, Krishnan Srinivasan, Parth Shah, Silvio Savarese, Li Fei-Fei, Animesh Garg, Jeannette Bohg · Shared by 4, including Matt Shaffer
Stanford University
Making Sense of Vision and Touch: Multimodal Representations for Contact-Rich Tasks
10 min · · Sound, smell, taste, touch, and vision – these are the five senses that humans use to perceive and understand the world. We are able to seamlessly combine these different senses when perceiving the… · Shared by 6, including Matt Shaffer
sites.google.com
CVRL
3 min · · Xiao Ma, Siwei Chen, David Hsu, Wee Sun Lee National University of Singapore · Shared by 4, including Matt Shaffer
rubenwiersma.nl
CNNs on Surfaces using Rotation-Equivariant Features
3 min · · Ruben Wiersma, Elmar Eisemann, and Klaus Hildebrandt Delft University of Technology Code + datasets Presentation Paper PDF Cite Abstract This paper is concerned with a fundamental problem in geometric… · Shared by 7, including Matt Shaffer
AI Papers
Deep End-to-end Causal Inference
1 min · · Causal inference is essential for data-driven decision making across domains such as business engagement, medical treatment or policy making. However, research on causal discovery and inference has… · Shared by 19, including Oleg Baskov, Matt Shaffer, AGI.Eth | MTL.Eth
sites.google.com
FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy
9 min · · Thomas Weng, Sujay Bajracharya, Yufei Wang, Khush Agrawal, David Held Robotics Institute, Carnegie Mellon University, Pittsburgh, PA [Paper on OpenReview] This work as has been accepted at CoRL 2021. · Shared by 4, including Matt Shaffer
AI Papers
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
1 min · · Recent self-supervised methods for image representation learning are based on maximizing the agreement between embedding vectors from different views of the same image. A trivial solution is obtained… · Shared by 7, including Matt Shaffer, Yann LeCun
drinkingcoder.github.io
LIFE: Lighting Invariant Flow Estimation
1 min · · We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on image pairs with small… · Shared by 5, 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