Stars
Bird frame for Raspberry Pi or your homelab - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. On an e-ink panel, a TV, or any screen.
A beamer template with some of Keynote's aesthetics
Code for blog post https://www.notion.so/Heuristics-Considered-Harmful-RL-With-Random-Rewards-Should-Not-Make-LLMs-Reason-21ba29497c4180ca86ffce303f01923d
SAILOR is an inverse RL algorithm that learns world and reward models to search at test-time and recover from mistakes.
A modern commutative diagram editor for the web.
Simple code for generating a color-coded latex table from raw data
LaTeX package and annotated examples for annotating equations using TikZ.
A bibliography and survey of the papers surrounding o1
A modern, highly customizable, responsive Jekyll template for course websites.
Official Implementation of SFM and the baselines in Jax.
RewardBench: the first evaluation tool for reward models.
Diffusing States and Matching Scores: A New Framework for Imitation Learning
world modeling challenge for humanoid robots
A recipe for online RLHF and online iterative DPO.
Recipes to train reward model for RLHF.
Reinforcement Learning via Regressing Relative Rewards
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
⚡️ Shockingly fast imitation learning algorithms via combining online and offline data engines. ⚡️
The official implementation of Self-Play Fine-Tuning (SPIN)
Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.
Contains JAX implementation of algorithms for inverse reinforcement learning
Learning Shared Safety Constraints from Multi-Task Demonstrations (NeurIPS 2023)
Train a language model to answer Slack messages as you.