Highlights
- Pro
Lists (1)
Stars
JAX bindings for the FlashAttention 3 kernels
Python Data Science Handbook: full text in Jupyter Notebooks
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
An implementation of PopArt normalization into IMPALA
Reference PyTorch implementation and models for DINOv3
An unofficial userspace driver for HID++ Logitech devices
🖱️🖥️JuhRadial MX is a Logi Options+ alternative for Linux - a beautiful radial menu for Logitech MX Master mice (KDE Plasma 6, Hyprland, Wayland)
Really Fast End-to-End Jax RL Implementations
Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication
Optimized primitives for collective multi-GPU communication
code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503
Documentation on how to access and use the Quick, Draw! Dataset.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
A bot which monitors immoscout24 and wg-gesucht.de for new flat offers and send requests to offers automatically.
[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delt…
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF problems. Trained with imitation learning on trajectories produced by LaCAM, it generates actions under p…
Master programming by recreating your favorite technologies from scratch.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Curated list of datasets and tools for post-training.
Implement a reasoning LLM in PyTorch from scratch, step by step
RAID is the largest and most challenging benchmark for AI-generated text detection. (ACL 2024)
A survey and reflection on the latest research breakthroughs in LLM-generated Text detection, including data, detectors, metrics, current issues and future directions.
Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free