6 papers
Quantum Flow Matching
Zidong Cui, Pan Zhang, Ying Tang
The flow matching has rapidly become a dominant paradigm in classical generative modeling, offering an efficient way to interpolate between two complex distributions. We extend thi…
Scalable Physics-Inspired Transformers for Spin Glasses
Lu Zhong, Wenli Duan, Jing Liu +2
Efficient sampling of the Boltzmann distribution in frustrated spin glasses is central to statistical mechanics and combinatorial optimization. Despite advances in machine-learning…
Irreversibility Enhances Quantum-Enhanced Markov-Chain Monte Carlo
Kefan Cao, Zidong Cui, Lei Wang +1
Detailed balance underlies conventional Markov-chain Monte Carlo (MCMC) algorithms. Yet in classical systems, breaking detailed balance generates irreversible probability currents…
Steering Dynamical Regimes of Diffusion Models by Breaking Detailed Balance
Haiqi Lu, Ying Tang
We show that deliberately breaking detailed balance in generative diffusion processes can accelerate the reverse process without changing the stationary distribution. Considering t…
Tracking large chemical reaction networks and rare events by neural networks
Jiayu Weng, Xinyi Zhu, Jing Liu +3
Chemical reaction networks are widely used to model stochastic dynamics in chemical kinetics, systems biology and epidemiology. Solving the chemical master equation that governs th…
SA-GAT-SR: Self-Adaptable Graph Attention Networks with Symbolic Regression for high-fidelity material property prediction
Junchi Liu, Ying Tang, Sergei Tretiak +2
Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches, particularly Graph Neural Networks (GNNs) for materials science. These method…