A novel approach enhances offline reinforcement learning performance through orthogonal-gradient updates.
― 7 min read
Haoran Xu
A new model improves speech-to-text efficiency in real-time applications.
― 6 min read
This study addresses fairness in medical imaging through synthetic data and new methods.
― 5 min read
A new method enhances offline RL using diffusion models for improved decision-making.
― 6 min read
New methods align 3D models with human preferences for better quality.
― 8 min read