This repository is a curated awesome list and survey companion for diffusion models applied to time series, spatio-temporal, and tabular data. It contains no executable code; the sole content is a large README.md that organizes hundreds of papers into a taxonomy by task (prediction, generation, imputation, anomaly detection, classification/regression, causal inference, event prediction, foundation models) and by application domain (healthcare, sequential recommendation, weather, energy, finance, AIOps, environment, traffic, manufacturing, audio, biology, communication). Each entry links to the paper and, where available, official code repositories. It is the companion to an ACM Computing Surveys paper (DOI 10.1145/3783986) and includes citation information, a Google Sheets taxonomy, and an overview figure. The repository is actively maintained with recent commits and welcomes pull requests. As a research resource, it is highly reproducible: all content is in the markdown file, with no dependencies, datasets, or environment setup required. Although classified as data_research due to its research orientation, it is not a data pipeline or ML codebase. Its value is as a reference index and literature map for researchers; the README itself is the reusable asset.
Time-MoE is a library/framework for training and deploying time series foundation models using a Mixture-of-Experts (MoE) architecture. It provides tools for training the TimeMoE model from scratch or fine-tuning pretrained versions, evaluating on benchmark datasets, and generating forecasts. The codebase is organized into modules for models, datasets, training utilities, and I/O operations, with a clear separation of concerns. Key features include efficient handling of large sequential datasets via sharded binary files, a custom MoE layer with load balancing loss, and integration with Hugging Face Transformers for model management and generation.
Zedis is a high-performance, Redis-compatible in-memory data store written in Zig. It implements the RESP protocol and supports core Redis data structures (strings, lists, TTL, pub/sub) along with advanced features: time-series with Gorilla compression, full-text search with BM25 and vector KNN (FLAT), probabilistic Bloom filters, and both AOF and RDB persistence. The architecture uses a multi-threaded server with a dedicated store thread for serialized command execution, custom budgeted allocators, and a lock-free client mailbox for message passing. While production-ready in capability, the project is explicitly designed for learning and experimentation and shows some documentation-to-code drift and a handful of unmaintained TODO items. It includes an extensive benchmark suite comparing against Valkey.
Automation Gateway is a reactive, configuration-driven bridge for industrial protocols (OPC UA, MQTT, PLC4X) that routes real-time process data to multiple time-series databases (InfluxDB, IoTDB, OpenSearch, Cassandra, PostgreSQL, etc.) and exposes it via GraphQL, MQTT, and OPC UA servers. The system runs as a single JVM or GraalVM native binary, orchestrated through YAML configuration files that define driver instances, logger sinks, and server endpoints. Its core architecture is built on Vert.x event bus for internal pub/sub messaging, with abstract base classes (DriverBase, LoggerBase) enabling consistent extension for new protocols or data stores. The gateway does not persist data itself; it acts as a real-time router with configurable buffering and queue reliability (memory-mapped disk queue). Key entry points include `App.kt` for the main application and `GraphQLServer.kt` for the administrative API, which supports JWT authentication, health checks, and dynamic component management. External dependencies include Eclipse Milo (OPC UA), HiveMQ MQTT client, PLC4X, Apache IoTDB Thrift, InfluxDB HTTP client, and various database drivers. The codebase is mature (v1.38) with active development, but carries some technical drift in the form of deprecated features still present in source code and a large set of reflection configurations for GraalVM native-image that require careful maintenance.
EchoTorch is a PyTorch-based research library for reservoir computing and echo state networks (ESNs). It implements multiple ESN variants, including a self-predicting ESN (SPESNCell), conceptor-based pattern manipulation with logic operations (AND, OR, NOT, PHI), a custom TimeTensor time-series wrapper, and supporting datasets such as Lorenz, Roessler, Mackey-Glass, NARMA, and MNIST. The repository is a library rather than an application: there are no web servers, CLIs, or service entry points; the primary interface is the Python package `echotorch` with submodules for neural network cells, datasets, transforms, costs, and utilities.