11 citations · 14 across the 8 of their papers we have counts for
4 papers · 1 filter
One Policy Is Enough: Single-Agent Reinforcement Learning Outperforms Tree Search for Chemistry Tool Learning
Armin Dariani, Sifan Wu, Bang Liu +1
Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for external tools. Tool use here…
The Grokked Illusion: True Equilibrium Mitigates Catastrophic Forgetting
Xiaotian Zhang, Lai Shun Chan, Yue Shang +2
While neural networks are typically evaluated by their training and test performance, these metrics do not reveal how robust a learned representation is. Recent studies have shown…
Is Grokking a Computational Glass Relaxation?
Xiaotian Zhang, Yue Shang, Entao Yang +1
Understanding neural network's (NN) generalizability remains a central question in deep learning research. The special phenomenon of grokking, where NNs abruptly generalize long af…
High-entropy Advantage in Neural Networks' Generalizability
Entao Yang, Xiaotian Zhang, Yue Shang +1
One of the central challenges in modern machine learning is understanding how neural networks generalize knowledge learned from training data to unseen test data. While numerous em…