Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍

A Minimalist, Batteries-included Repository for Advancing World Model Science.

An Agentic System for Scalable Articulated 3D Asset Generation

[NeurIPS 2025] LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans

A controllable and interactive simulation framework for vision research.

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

Allen Institute for AI: WildDet3D: Scaling Promptable 3D Detection in the Wild

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

A platform for reproducible world model research and evaluation

AI agents running research on single-GPU nanochat training automatically

Create beautiful slides on the web using a coding agent's frontend skills

2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，思想类，数学类，人物传记书籍

RealSee3D: A multi-view RGB-D dataset combining real-world captures and procedurally generated scenes, with extensible annotations for diverse 3D vision research.

NVIDIA Isaac Sim™ is an open-source application on NVIDIA Omniverse for developing, simulating, and testing AI-driven robots in realistic virtual environments.

Interactive look at the advisees and academic descendants of Chris Manning, generated from OpenReview.

Official implementation of NeurIPS 2025 paper "SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent"

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Information about procedural city generation

CVPR 2024: Language Guided Generation of 3D Embodied AI Environments.

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D