TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Dexbotic: Open-Source Vision-Language-Action Toolbox

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

Native and Compact Structured Latents for 3D Generation

[AAAI 26 Oral] Official implementation of "FreeGaussian: Annotation-free Control of Articulated Objects via 3D Gaussian Splats with Flow Derivatives"

Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation

SAM 3D Objects with Multi-view Images

Tools to build pytorch3d wheels for linux

The first Interleaved framework for textual reasoning within the visual generation process

The official implementation of The paper "Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation"

Team Comet's 2025 BEHAVIOR Challenge Codebase

Are Video Models Ready as Zero-shot Reasoners?

每日arxiv论文更新；Topic：EmbodiedAI，MLLM，Vision- Language- Navigation

3D Gaussian Splat Editor

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

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Fully Open Framework for Democratized Multimodal Training

Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)

EO: Open-source Unified Embodied Foundation Model Series

paper code

Reference PyTorch implementation and models for DINOv3

[Neurips'24 Spotlight] Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

Text-audio foundation model from Boson AI

Easy Data Preparation with latest LLMs-based Operators and Pipelines.