gradient-flow

Pytorch implementation of DGflow (ICLR 2021).

Solver for differential algebraic equations

Discretized Wasserstein Particle Flows of a MMD-regularized f-divergence functional.

Variational Filtering via Wasserstein Gradient Flow

[NeurIPS 2022] Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again by Ajay Jaiswal*, Peihao Wang*, Tianlong Chen, Justin F Rousseau, Ying Ding, Zhangyang Wang

Numeric simulation of a 2D Bose Einstein condensate

Code for paper: "Improved Residual Network Based on Norm-Preservation for Visual Recognition" https://doi.org/10.1016/j.neunet.2022.10.023

[NeurIPS'25] Sequence Modeling with Spectral Mean Flows, in PyTorch

High-Dimensional Analysis of Gradient Flow for the Matrix Factorization Problem

A detailed-balanced chemical reaction network realized as a gradient flow, where equilibrium propagation is rigorous — the chemistry computes its own weight update (verified: local update == true gradient). Audits 'who computes the update?' across a co-location spectrum vs an offline ceiling. Part of physical-learning-substrates.

Unity Equilibrium Theory - Dual-field gradient flow simulator for phase dynamics

Supplementary code for the paper 'Are GATs Out of Balance?' to be published at NeurIPS 2023

Discreteness as the Late-Time Limit of a Smooth Flow

Kinetic Adaptation via Wasserstein Heuristics and Identity

Accelerated Stein Variational Gradient Descent for sampling for densities

Independent research on inactive-neuron entry-exit dynamics, with mathematical analysis, archived experiments, reproducibility guides, and a connected research roadmap.