• 👨🏼‍💻 I’m a Research Scientist andTech Lead at ByteDance, San Jose, USA.
• 👨🏼‍💻 I was a Research Scientist at Tencent, Shanghai.
• 🔭 I’m currently working onGenerative AI andMultimodal Models, including Language Driven Model and 3DAIGC.
• 📖 Recent works:Motion-Latent-Diffusion andMotionGPT, aunified anduser-friendly motion-language model usingLLMs.
• 📖 Recent works:Paint3D, alighting-less texture diffusion model.
• 📖 Recent works:AppAgent, a multimodalagent for smartphone apps.
• 📖 Recent works:LL3DA andM3DBench , a multimodal-language 3D assistant and benchmark.

PinnedLoading

1. OpenMotionLab/MotionGPTOpenMotionLab/MotionGPTPublic

   [NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs

   Python 1.6k 99

2. OpenTexture/Paint3DOpenTexture/Paint3DPublic

   [CVPR 2024] Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model

   Python 731 37

3. motion-latent-diffusionmotion-latent-diffusionPublic

   [CVPR 2023] Executing your Commands via Motion Diffusion in Latent Space, a fast and high-quality motion diffusion model

   Python 626 57

4. TencentQQGYLab/AppAgentTencentQQGYLab/AppAgentPublic

   AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

   Python 5.6k 622

5. NeuralCarver/MichelangeloNeuralCarver/MichelangeloPublic

   [NeurIPS 2023] Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

   Python 405 16

6. OpenMeshLab/MeshXLOpenMeshLab/MeshXLPublic

   [NeurIPS 2024] MeshXL: Neural Coordinate Field for Generative 3D Foundation Models, a 3D fundamental model for mesh generation

   Python 302 11