Stars
[NeurIPS 2025 𝐒𝐩𝐨𝐭𝐥𝐢𝐠𝐡𝐭] AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
Sotopia-π: Interactive Learning of Socially Intelligent Language Agents (ACL 2024)
Public repository for "Think Twice: Perspective-Taking Improves Large Language Models’ Theory-of-Mind Capabilities".
Generative Agents: Interactive Simulacra of Human Behavior
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
[2025 NeurlPS Spotlight] MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…
Foundation 3D ViT model for volumetric head CT - Nature Biomedical Engineering
LaTeX files for the Deep Learning book notation
A repository accompanying the PARTNR benchmark for using Large Planning Models (LPMs) to solve Human-Robot Collaboration or Robot Instruction Following tasks in the Habitat simulator.
A flexible, high-performance 3D simulator for Embodied AI research.
API to run VirtualHome, a Multi-Agent Household Simulator
An Open-Ended Embodied Agent with Large Language Models
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.
A library for advanced large language model reasoning
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Official Repository of Absolute Zero Reasoner
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environment…
[CVPR 2025] EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance