rose-stl-lab Goto Github PK

approximately-equivariant-nets

autonpp

Efficient computation of temporal point process intensity using automatic integration

autoode-dsl

autostpp

Automatic Integration for Neural Spatio-Temporal Point Process models (AI-STPP) is a new paradigm for exact, efficient, non-parametric inference of point process. It is capable of learning complicated underlying intensity functions, like a damped sine wave.

copulacpts

Code for Copula conformal prediction paper (ICLR 2024)

cs-6140-fall-2018

Final project page for CS 6140

danp

Domain Adversarial Neural Process

deepstpp

dive

Disentangled Imputed Video autoEncoder (DIVE)

dyffusion

[NeurIPS 2023] A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

dynamic-adaptation-network

ecco

equivariant-net

fs-cap

few-shot compound activity regression

gpu-benchmark

gradient-flow-symmetry

[ICLR 2023] Symmetries, flat minima, and the conserved quantities of gradient flow

hdr-il

hierarchical-neural-processes

interactive-neural-process

ir2rgb

IR to RGB video translation

lab-wiki

Knowledge Sharing

liegan

limo

generative model for drug discovery

lyapunov-regularized-forecaster

mcd

Implementation of the ICML 2024 paper "Discovering Mixtures of Structural Causal Models from Time Series Data"

mfrnp

[ICML 2024] Multi Fidelity Residual Neural Process

mrtl

Multiresolution Tensor Learning

mrtl-st

multi-fidelity-deep-active-learning

nautilus_tutorial