verl: Volcano Engine Reinforcement Learning for LLMs

Lock, Stock, and Two Smoking MicroVMs. Create and manage the lifecycle of MicroVMs backed by containerd.

Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

Official Repository of "Learning to Reason under Off-Policy Guidance"

RLP: Reinforcement as a Pretraining Objective

The Agentic Commerce Protocol (ACP) is an interaction model and open standard for connecting buyers, their AI agents, and businesses to complete purchases seamlessly. The specification is currently…

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

[NeurIPS'25] HyRF: Hybrid Radiance Fields for Efficient and High-quality Novel View Synthesis

MAPO: MIXED ADVANTAGE POLICY OPTIMIZATION

Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

Trio – a friendly Python library for async concurrency and I/O

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

[EMNLP 2025] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

laptop

NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.

My C++ solutions for LeetCode questions.

Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training

The core CUA for Project Navi

The Cursor for Writing

An algorithm that implements intelligence based on a Method pool (a collection containing multiple types of functions). 一种基于方法池（包含多种类型的函数的集合）实现智能的算法

Geospatial Mechanistic Interpretability of Large Language Models

A library for mechanistic interpretability of GPT-style language models

A repository for awesome resources in mechanistic interpretability

Lime: Explaining the predictions of any machine learning classifier