Search Results for author:
Found 11 papers, 4 papers with code
Video as the New Language for Real-World Decision Making
Moreover, we demonstrate how, like language models, video generation can serve as planners, agents, compute engines, and environment simulators through techniques such as in-context learning, planning and reinforcement learning.
Investigating the role of model-based learning in exploration and transfer
Our results show that intrinsic exploration combined with environment models present a viable direction towards agents that are self-supervised and able to generalize to novel reward functions.
Transframer: Arbitrary Frame Prediction with Generative Models
We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction.
Procedural Generalization by Planning with Self-Supervised World Models
One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks.
Ranked #1 on
Meta-Learning
on ML10
(Meta-test success rate (zero-shot) metric)
CoBERL: Contrastive BERT for Reinforcement Learning
Many reinforcement learning (RL) agents require a large amount of experience to solve tasks.
Predicting Video with VQVAE
In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community.
Ranked #10 on
Video Prediction
on Kinetics-600 12 frames, 64x64
Representation Learning via Invariant Causal Mechanisms
Self-supervised learning has emerged as a strategy to reduce the reliance on costly supervised signal by pretraining representations only using unlabeled data.
Ranked #77 on
Self-Supervised Image Classification
on ImageNet
The Pose Knows: Video Forecasting by Generating Pose Futures
First we explicitly model the high level structure of active objects in the scene---humans---and use a VAE to model the possible future movements of humans in the pose space.
Ranked #2 on
Human Pose Forecasting
on Human3.6M
(CMD metric)
An Uncertain Future: Forecasting from Static Images using Variational Autoencoders
We show that our method is able to successfully predict events in a wide variety of scenes and can produce multiple different predictions when the future is ambiguous.
Dense Optical Flow Prediction from a Static Image
Because our CNN model makes no assumptions about the underlying scene, it can predict future optical flow on a diverse set of scenarios.
Patch to the Future: Unsupervised Visual Prediction
In this paper we present a conceptually simple but surprisingly powerful method for visual prediction which combines the effectiveness of mid-level visual elements with temporal modeling.
