Time-Series Anomaly Detection | Algorithms + Datasets + Tutorials

The official implementation of Time-RCD for zero-shot time series anomaly detection, ICML 2026

Large corpus for TimeRCD

Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).

[ECCV2026] Official repo for paper "SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation".

[SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

1078 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — from PRDs and postmortems to decoding a lease, budgeting your energy in spoons, and rehearsing the hardest conversation.…

#1 Persistent memory for AI coding agents based on real-world benchmarks

Time-Series-Optimized Transformer for Observability

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Official code for TimeCraft: A Time Series Generation Framework for Real-World Applications

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

Official Anytype client for MacOS, Linux, and Windows

A Raspberry Pi jukebox, playing local music, podcasts, web radio and streams triggered by RFID cards, web app or home automation. All plug and play via USB. GPIO scripts available.

Native and Compact Structured Latents for 3D Generation

Book and material for the course "Time series analysis with Python" (STA-2003)

The official implementation of Value Flows

The best ChatGPT that $100 can buy.

A curated list of Claude Skills.

Reference PyTorch implementation and models for DINOv3

Official Repo for Self-Forcing++ High Quality Long Video Generation

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Wan: Open and Advanced Large-Scale Video Generative Models

A collection of papers on diffusion models for 3D generation.

Official repository for the paper "Orientation Matters: Making 3D Generative Models Orientation-Aligned" (NeurIPS 2025)

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.