Pinned Loading

1. cosmos cosmos Public

   Forked from NVIDIA/cosmos

   NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

   Jupyter Notebook

2. Qwen3-VL Qwen3-VL Public

   Forked from QwenLM/Qwen3-VL

   Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

   Jupyter Notebook

3. PKU-YuanGroup/Open-Sora-Plan PKU-YuanGroup/Open-Sora-Plan Public

   This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

   Python 12.2k 1.1k

4. Point-MAE Point-MAE Public

   [ECCV2022] Masked Autoencoders for Point Cloud Self-supervised Learning

   Python 630 73

5. LanguageBind LanguageBind Public

   Forked from PKU-YuanGroup/LanguageBind

   【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

   Python

6. MoE-LLaVA MoE-LLaVA Public

   Forked from PKU-YuanGroup/MoE-LLaVA

   Mixture-of-Experts for Large Vision-Language Models

   Python