Implementation of "Detecting Anomalous Event Sequences with Temporal Point Processes" (NeurIPS 2021)

Implementation of "Neural Jump-Diffusion Temporal Point Processes" (ICML 2024 Spotlight)

Code and real data for "Counterfactual Temporal Point Processes", NeurIPS 2022

This repository contains recent background materials, current works, and codes for researching in TPP.

Implementation of "Conformal Anomaly Detection in Event Sequences" (ICML 2025)

PyTorch-Lightning implementation of Meta Temporal Point Processes

The official Pytorch implementation of paper "Patent Citation Dynamics Modeling via Multi-Attention Recurrent Networks""

Paper currently under review.

Master thesis title: "Towards Event Sequence Foundation Models: exploring temporal point process transformers for power grid fault prediction" Dataset and modelling infrastructure for modelling "event streams": sequences of continuous time, multivariate events with complex internal dependencies.

Dual Network Hawkes Process -- Analyzing Topic Transitions in Text-Based Social Cascades

Implementation of "Multiple Hypothesis Testing for Anomaly Detection in Multi-type Event Sequences" (ICDM 2023)

From-scratch PyTorch implementation of the Transformer Hawkes Process: multi-head attention, three temporal encodings, and a Monte Carlo log-likelihood loss, validated against closed-form Hawkes process theory. Documents a real data-leakage bug found via likelihood sanity-checking, not just unit tests.