zrrskywalker / point-m2ae Goto Github PK

🌱 I'm Renrui Zhang, a Ph.D. candidate in MMLab, CUHK.

• [2017-2021] 🎉 I received my B.E. degree from Peking University, awarded Outstanding Graduates (top 5%).
• [2020-2021] I worked as a visiting student in University of Pennsylvania, supervised by Prof. Jianbo Shi.
• [2021-Now] 💪 I'm pursing my Ph.D. in MMLab, CUHK, supervised by Prof. Hongsheng Li and Prof. Xiaogang Wang.
• [2021-Now] I'm working as a research intern at Shanghai AI Lab, supervised by Dr. Peng Gao.

• Multi-modality Alignment: ImageBind-LLM and Point-Bind
• Personalization of Segment Anything: PerSAM and PerSAM-F
• Instruction Tuning of LLaMA: LLaMA-Adapter -> LLaMA-Adapter V2 -> ImageBind-LLM and Point-LLM
• Efficient Adaption of CLIP in 2D: CLIP-Adapter -> Tip-Adapter -> CaFo, APE
• MAE for 3D Point Clouds: Point-M2AE -> I2P-MAE
• Cross-modal Adaption of CLIP in 3D: PointCLIP -> PointCLIP V2
• Non-Parametric 3D Analysis: Point-NN and Point-PN
• Camera-based 3D Object Detection: MonoDETR, MonoDETR-MV -> TiG-BEV

• [2023-09-04] Release the paper of Point-Bind & Point-LLM, aligning 3D with multi-modality for LLMs.
• [2023-08-26] Release the final code of MonoDETR, achieving more stable results for 3D detection.
• [2023-06-05] Release the code of Point-Bind for aligning different modalities with 3D point clouds.
• [2023-05-29] Release the code of ImageBind-LLM for multi-modality instruction tuning of LLaMA.
• [2023-05-05] Release the paper PerSAM and code for personalizing Segment Anything within 10 seconds.
• [2023-04-29] Release the paper LLaMA-Adapter V2 and code for stronger multi-modal reasoning.
• [2023-04-16] Release the training code of LLaMA-Adapter.
• [2023-04-11] Release the code of Point-PN.
• [2023-04-03] Release the code of Point-M2AE and I2P-MAE.
• [2023-04-01] Release CaFo cascaded with ChatGPT and Stable Diffusion.