Stars
The Tensor Algebra Compiler (taco) computes sparse tensor expressions on CPUs and GPUs
PDF exporter for HTML presentations
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
Fast, accurate & comprehensive text measurement & layout
Sioyek is a PDF viewer with a focus on textbooks and research papers
SGLang is a high-performance serving framework for large language models and multimodal models.
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Building Open-Ended Embodied Agents with Internet-Scale Knowledge
CausalFlows: A library for Causal Normalizing Flows in Pytorch
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
A better file browser and calendar for Obsidian, inspired by Apple Notes, Bear, Evernote and Day One.
This repository has been made during my master's thesis : Probing GNN representations
SHARPIE: Shared Human-AI Reinforcement Learning Platform for Interactive Experiments
This repository will host the material for the ESSLLI 2025 course "Neurosymbolic learning: an introductory course to theory and applications"
Lightweight plotting to the terminal. 4x resolution via Unicode.
The Aether II is the sequel to the highly popular dimension mod "The Aether" for modern versions of Minecraft.
The original "The Aether" mod, rewritten and ported to modern Minecraft versions.
We integrate discrete diffusion models with neurosymbolic predictors for scalable and calibrated learning and reasoning
The official repo of the paper "MMLongBench Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly"
Train transformer language models with reinforcement learning.
List of papers on hallucination detection in LLMs.
An experimental language for causal reasoning
An Obsidian plugin for day planning with a clean UI and a simple task format