68 citations · 162 across the 11 of their papers we have counts for
12 papers
Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems
Xingchen Zou, Yuhao Yang, Zheng Chen +4
We introduce Traffic-R1, a 3B-parameter foundation model with human-like reasoning for Traffic signal control (TSC), developed via self-exploration and iterative reinforcement of L…
On the Interpolation Effect of Score Smoothing in Diffusion Models
Zhengdao Chen
Diffusion models have achieved remarkable progress in various domains with an intriguing ability to produce new data that do not exist in the training set. In this work, we study t…
Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space
Zhengdao Chen
To characterize the function space explored by neural networks (NNs) is an important aspect of learning theory. In this work, noticing that a multi-layer NN generates implicitly a…
A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks
Xinyi Wu, Zhengdao Chen, William Wang +1
Oversmoothing is a central challenge of building more powerful Graph Neural Networks (GNNs). While previous works have only demonstrated that oversmoothing is inevitable when the n…
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna
To understand the training dynamics of neural networks, prior studies have considered the mean-field limit of two-layer neural networks as the width tends to infinity, establishing…
On Feature Learning in Neural Networks with Global Convergence Guarantees
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna
We study the optimization of wide neural networks (NNs) via gradient flow (GF) in setups that allow feature learning while admitting non-asymptotic global convergence guarantees. F…
On Graph Neural Networks versus Graph-Augmented MLPs
Lei Chen, Zhengdao Chen, Joan Bruna
From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Percept…
A Dynamical Central Limit Theorem for Shallow Neural Networks
Zhengdao Chen, Grant M. Rotskoff, Joan Bruna +1
Recent theoretical works have characterized the dynamics of wide shallow neural networks trained via gradient descent in an asymptotic mean-field limit when the width tends towards…
Can Graph Neural Networks Count Substructures?
Zhengdao Chen, Lei Chen, Soledad Villar +1
The ability to detect and count certain substructures in graphs is important for solving many tasks on graph-structured data, especially in the contexts of computational chemistry…
Symplectic Recurrent Neural Networks
Zhengdao Chen, Jianyu Zhang, Martin Arjovsky +1
We propose Symplectic Recurrent Neural Networks (SRNNs) as learning algorithms that capture the dynamics of physical systems from observed trajectories. An SRNN models the Hamilton…
On the equivalence between graph isomorphism testing and function approximation with GNNs
Zhengdao Chen, Soledad Villar, Lei Chen +1
Graph Neural Networks (GNNs) have achieved much success on graph-structured data. In light of this, there have been increasing interests in studying their expressive power. One lin…
Structure-preserving numerical integrators for Hodgkin-Huxley-type systems
Zhengdao Chen, Baranidharan Raman, Ari Stern
Motivated by the Hodgkin-Huxley model of neuronal dynamics, we study explicit numerical integrators for "conditionally linear" systems of ordinary differential equations. We show t…