Assistant Professor, University of Montreal
4 papers at NeurIPS 2025
We stabilize gradients for training increasingly deep reinforcement learning agents by using a second-order optimizer and residual connections
Measuring neuronal activity via activations is ineffective in complex agents, as these values do not reflect true learning capacity. We introduce GraMa, which offers robust quantification and resetting guidance across various network architectures.
We show that discrete representation of images improve unconditional and compositional generation
