Group Diffusion Policy Optimization

Your own personal AI assistant. Any OS. Any Platform.

SoFlow: Solution Flow Models for One-Step Generative Modeling

MoE training for Me and You and maybe other people

SR-DiT Speedrunning ImageNet Diffusion

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

[Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

dLLM: Simple Diffusion Language Modeling

Equal-area A5 spatial index functions for PostgreSQL, implemented with pgrx.

An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.

A recursive, reflective POETRY algorithm variant using Goedel-Prover-V2

A Gym for Agentic LLMs

An interface library for RL post training with environments.

Training framework with a goal to explore the frontier of sample efficiency of small language models

Training API and CLI

A Lightweight LLM Post-Training Library

Large multi-modal models (L3M) pre-training.

AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

Benchmarking Optimizers for LLM Pretraining

Uncertain<T> - A Swift library for uncertainty-aware programming.

Train LLM on Hugging Face infra

🔀 yet another mixture of experts

Implementation for FP8/INT8 Rollout for RL training without performence drop.

Solving Hilbert's sixth problem in Lean