11 citations · 14 across the 8 of their papers we have counts for
9 papers
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…
Tunneling the Loss Landscape: Bypassing Memorization with Monte Carlo Parameter Swapping
Lai Shun Chan, Xiaotian Zhang, Yue Shang +2
Grokking is a striking phenomenon in neural network training, where a model can undergo a prolonged period of pure memorization before abrupt generalization. While previous works h…
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…
Machine learning-informed structuro-elastoplasticity predicts ductility of disordered solids
Hongyi Xiao, Ge Zhang, Entao Yang +5
All solids yield under sufficiently high mechanical loads. Below yield, the mechanical responses of all disordered solids are nearly alike, but above yield every different disorder…
Structuro-elasto-plasticity (StEP) model for plasticity in disordered solids
Ge Zhang, Hongyi Xiao, Entao Yang +5
Elastoplastic lattice models for the response of solids to deformation typically incorporate structure only implicitly via a local yield strain that is assigned to each site. Howev…
Understanding Creep Suppression Mechanism in Polymer Nanocomposites through Machine Learning
Entao Yang, James F. Pressly, Bharath Natarajan +3
While recent efforts have shown how local structure plays an essential role in the dynamic heterogeneity of homogeneous glass-forming materials, systems containing interfaces such…
The Role of Local Structure in the Enhanced Dynamics of Deformed Glasses
Entao Yang, Robert A. Riggleman
External stress can accelerate molecular mobility of amorphous solids by several orders of magnitude. The changes in mobility are commonly interpreted through the Eyring model, whi…