Stars
Continuous Thought Machines, because thought takes time and reasoning is a process.
✨✨R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
Official Repository of Absolute Zero Reasoner
A curated collection of neuroscience tasks with a common interface.
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper list for Modern Hopfield Networks
Implementation of 'RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning'
SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms
Model Context Protocol(MCP) 编程极速入门
Add a tqdm progress bar to your JAX scans and loops.
Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.co/NX-AI/xLSTM-7b.
Generate graph/data embeddings multiple ways
Code for the paper "Goals as Reward Producing Programs"