Mon Jun 13 2022
Tue Jun 07 2022

Generating Long Videos of Dynamic Scenes

Computer Vision
Computer Vision
Deep Learning
Video production

Demonstrates SotA performance in producing long videos with realistic motion and changes in content by leveraging a two-phase training strategy.

Can be used to create more realistic and engaging videos for marketing or training purposes

On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning

Reinforcement Learning
Machine Learning
Deep Learning
Reinforcement Learning

Multi-task pretraining and fine-tuning outperforms meta-RL

Can inform decision making when choosing between meta-learning and fine-tuning approaches in reinforcement learning

Mon Jun 06 2022