Optimization

A 14B-parameter chemical reasoning LLM enhanced with atomized functional group knowledge and mix-sourced distillation …

Introduces displacement interpolation to prove ground state uniqueness via optimal transport, establishing foundations …

A continuous-time normalizing flow using stochastic interpolants and quadratic loss to bypass costly ODE …

A simulation-free framework for training Continuous Normalizing Flows using Conditional Flow Matching and Optimal …

A unified ODE-based framework for generative modeling and domain transfer that learns straight paths for fast 1-step …

Introduces ODE-Nets, a continuous-depth neural network model parameterized by ODEs, enabling constant memory …

Theoretical paper proving the equivalence between training Denoising Autoencoders and performing Score Matching on a …

Comprehensive user guide for the Embedded-Atom Method (EAM), covering theory, potential fitting, and applications to …

Seminal 1994 paper introducing MDNs to model arbitrary conditional probability distributions using neural networks.

A seminal kinetic model using coupled ODEs to explain temporal self-organization and mixed-mode oscillations on platinum …

In situ XRD validation of the oxide model driving kinetic rate oscillations in high-pressure CO oxidation on supported …

Hyperbolic Algorithm adds second-order derivatives to Langevin dynamics, reducing systematic errors to O(ε²) for lattice …