Yedi Zhang
- Reposted by Yedi ZhangWhy don’t neural networks learn all at once, but instead progress from simple to complex solutions? And what does “simple” even mean across different neural network architectures? Sharing our new paper @iclr_conf led by Yedi Zhang with Peter Latham arxiv.org/abs/2512.20607
- Reposted by Yedi Zhang[Not loaded yet]
