Specification and documentation for Agent Skills

Drawing Bayesian networks, graphical models, tensors, technical frameworks, and illustrations in LaTeX.

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

Official Implementation of "Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation"

A benchmark to test the ability of LLMs and VLMs to do mazes in various conditions.

Official implementation of Think Global, Act Local: Dual-scale GraphTransformer for Vision-and-Language Navigation (CVPR'22 Oral).

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Vision-and-Language Navigation in Continuous Environments using Habitat

Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR-25)

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

Official style files for papers submitted to venues of the Association for Computational Linguistics

The code for NeurIPS 2025 paper "A-Mem: Agentic Memory for LLM Agents"

https://hrl.boyuai.com/

A large-scale benchmark and learning environment.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

记录个人博士期间学习机器人相关的过程

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Dexbotic: Open-Source Vision-Language-Action Toolbox

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

A minimalist MVP demonstrating a simple yet profound insight: aligning AI memory with human episodic memory granularity. Shows how this single principle enables simple methods to rival complex memo…

Expert Specialized Fine-Tuning

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval