#
Starred repositories
A modern framework for time series analysis and forecasting, offering everything from simple automated fits to fine-grained parameter control, with native support for diverse data types.
Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
Official repository of the 2025 paper, LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra.
Tutorial Materials for the paper "Evaluation & Benchmarking of LLM Agents: A Survey" published in KDD 2025 Conference.
Simplifying reinforcement learning for complex game environments
Polaris is a music streaming application, designed to let you enjoy your music collection from any computer or mobile device.
Notebooks for AI-Powered Decision Making Under Uncertainty
Schedule-Free Optimization in PyTorch
GoogleDrive-Protected-PDF-Downloader is a JavaScript-based tool designed to help users download and print protected PDFs from Google Drive. This tool handles images stored as blob URLs within Googl…
[SIGMOD 2024] CAFE: Towards Compact, Adaptive, and Fast Embedding for Large-scale Recommendation Models
A playbook for systematically maximizing the performance of deep learning models.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
A pytorch port of google-research/google-research/robust_loss/
Simulation files for Schultzberg & Ankargren blogpost 2023
Implements the paper "Wukong: Towards a Scaling Law for Large-Scale Recommendation" from Meta.
TensorDict is a pytorch dedicated tensor container.
Unified storage framework for the entire machine learning lifecycle
A modern Anki custom scheduling based on Free Spaced Repetition Scheduler algorithm
ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering
A memory efficient DLRM training solution using ColossalAI
Making large AI models cheaper, faster and more accessible
Large batch training of CTR models based on DeepCTR with CowClip.
Experiment tracking server focused on speed and scalability
[KDD 2022] AutoShard: Automated Embedding Table Sharding for Recommender Systems
PRQL is a modern language for transforming data — a simple, powerful, pipelined SQL replacement
Flexible Python configuration system. The last one you will ever need.
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️