Minimal open-source implementation of AlphaProof [WIP]

CausalFlows: A library for Causal Normalizing Flows in Pytorch

MMhops-R1: Multimodal Multi-hop Reasoning

Open-source release accompanying Gao et al. 2025

We integrate discrete diffusion models with neurosymbolic predictors for scalable and calibrated learning and reasoning

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Cyberpandino cluster

Sparse and Structured Tensor Compiler

Django App per l'autocompilazione dei moduli missione

Port of the book Think Python to the Julia programming language

Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"

[ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter

Autonomous GPU Kernel Generation via Deep Agents

[BMVC 2025 Oral] HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization

Improving Human Motion Plausibility with Body Momentum [BMVC 2025]

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

EGGROLL in C, integer-first training

minimal DL library in C: 24 NAIVE cuda/cpu ops, autodiff engine, python API (ops bindings/layers/models), tensor abstraction, strides, complex indexing (multi-dim slices like numpy), computation-gr…

Official implementation of "Continuous Autoregressive Language Models"

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

A library to analyze PyTorch traces.

slime is an LLM post-training framework for RL Scaling.

Transform your project into an explorable 3D world

A graph-based code navigation plugin for Visual Studio

Dissecting data structures