Brain-Inspired Attention Model for Object Counting
Published in International Conference on Neural Information Processing, 2022
Recommended citation:
Download Paper
Publications
You can also find my articles on my Google Scholar profile.
Conference Papers
Preprints
Outcome level mode collapse in reinforcement learning
Published in arXiv, 2026
We show that the objective function in reinforcement learning is destined to mode collapse. And our proposed solution is to use inverse probability scaling to the terminal rewards.
Recommended citation:
Download Paper
Physical Plausibility Failure Modes with Matryoshka Transcoders
Published in arXiv, 2025
Recommended citation:
Download Paper