Pretraining Recurrent Networks without Recurrence

Unified framework for robot learning built on NVIDIA Isaac Sim

A set of examples based on verl for end-to-end RL training recipes.

Official repository of DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing

The official repo of EurekaClaw

The batteries-included agent harness.

Build resilient agents.

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

A leaky integrate-and-fire computational model of the Drosophila brain

A neuromechanical model of adult Drosophila melanogaster.

MuJoCo fruit fly body model and locomotion RL tasks

AI agents running research on single-GPU nanochat training automatically

OpenClaw AI assistant recipes for MIT Engaging HPC (Apptainer/SLURM)

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

The best OSS video generation models, created by Genmo

Wan: Open and Advanced Large-Scale Video Generative Models

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

TradingAgents: Multi-Agents LLM Financial Trading Framework

AllenAI's post-training codebase

Labs for MIT 6.S184/6.S975, IAP 2025/2026

Understanding R1-Zero-Like Training: A Critical Perspective

SGLang is a high-performance serving framework for large language models and multimodal models.

LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.

A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.

SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）

Implementation of various evolutionary algorithms, starting with evolutionary strategies