-
Uber AI Labs & ML Collective
- San Francisco, CA
Stars
Minimal and highly hackable implementation of Looped Transformers with GPT
Small reproducible problems for Sutro Group's energy-efficient learning research
A collection of agent skills for CAD, robotics and hardware design
100M tokens. Infinite compute. Lowest val loss wins.
An asyncio-native Kalshi client for Python.
Puzzles for exploring transformers
Official implementation of Transformer Neural Processes
A Conversational Speech Generation Model
maximal update parametrization (µP)
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.
A framework for Claude Opus to intelligently orchestrate subagents.
Anim-400K: A dataset designed from the ground up for automated dubbing of video
The code base for paper: "ReAcTable: Enhancing ReAct for Table Question Answering"
DSPy: The framework for programming—not prompting—language models
Official implementation of AnimateDiff.
Machine Learning Engineering Open Book
Vector (and Scalar) Quantization, in Pytorch
Code and data for ICCV23 work "Deep Geometrized Cartoon Line Inbetweening"
Send webpages, documents and bookmarks to kindle
A lightweight coding agent for open models like Deepseek, Kimi, and Qwen
A guidance language for controlling large language models.
Semantic photo search for the command line
Streamlit component that allows Plotly events to bubble back up to streamlit. Makes Plotly charts interactive!
A probabilistic programming language that combines automatic differentiation, automatic marginalization, and automatic conditioning within Monte Carlo methods.
Smart contracts and specification of the AMM protocol on top of the Ergo blockchain
High speed mini-batch data reading & preprocessing from BigQuery.