
-
Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image
We present Worldsheet, a method for novel view synthesis using just a si...
read it
-
FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
A majority of approaches solve the problem of video frame interpolation ...
read it
-
Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion
Hierarchical learning has been successful at learning generalizable loco...
read it
-
Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
Learning long-term dynamics models is the key to understanding physical ...
read it
-
One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control
Reinforcement learning is typically concerned with learning control poli...
read it
-
Locally Masked Convolution for Autoregressive Models
High-dimensional generative models have many applications including imag...
read it
-
Planning to Explore via Self-Supervised World Models
Reinforcement learning allows solving complex tasks, however, the learni...
read it
-
Sparse Graphical Memory for Robust Planning
To operate effectively in the real world, artificial agents must act fro...
read it
-
Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
We study a generalized setup for learning from demonstration to build an...
read it
-
Self-Supervised Exploration via Disagreement
Efficient exploration is a long-standing problem in sensorimotor learnin...
read it
-
try it
-
Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Contemporary sensorimotor learning approaches typically start with an ex...
read it
-
Large-Scale Study of Curiosity-Driven Learning
Reinforcement learning algorithms rely on carefully engineering environm...
read it
-
Compositional GAN: Learning Conditional Image Composition
Generative Adversarial Networks (GANs) can produce images of surprising ...
read it
-
Learning Instance Segmentation by Interaction
We present an approach for building an active agent that learns to segme...
read it
-
Zero-Shot Visual Imitation
The current dominant paradigm for imitation learning relies on strong su...
read it
-
Investigating Human Priors for Playing Video Games
What makes humans so good at solving seemingly complex video games? Unli...
read it
-
Toward Multimodal Image-to-Image Translation
Many image-to-image translation problems are ambiguous, as a single inpu...
read it
-
Curiosity-driven Exploration by Self-supervised Prediction
In many real-world scenarios, rewards extrinsic to the agent are extreme...
read it
-
Learning Features by Watching Objects Move
This paper presents a novel yet intuitive approach to unsupervised featu...
read it
-
Context Encoders: Feature Learning by Inpainting
We present an unsupervised visual feature learning algorithm driven by c...
read it
-
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
We present an approach to learn a dense pixel-wise labeling from image-l...
read it
-
Fully Convolutional Multi-Class Multiple Instance Learning
Multiple instance learning (MIL) can reduce the need for costly annotati...
read it
-
Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning
We develop methods for detector learning which exploit joint training ov...
read it