We rethink the role of positional encoding in 3D representation learning, and propose Positional Prompt Tuning, a simple but efficient method for transfer learning.

We collect diverse images and prompts, and utilize GPT-4o for automated evaluation aligned with human preference.

We present ShapeLLM, the first 3D Multimodal Large Language Model designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages.

We present DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models empowered with frequently overlooked synergy between multimodal comprehension and creation.

We achieve rapid, multi-category 3D conditional generation by sharing the merits of different representations. VPP can generate 3D shapes less than 0.2s using a single RTX 2080Ti.

We enhance the utilization of color information to improve 3D scene self-supervised learning.

We propose contrast guided by reconstruct to mitigate the pattern differences between two self-supervised paradigms.

We propose to use autoencoders as cross-modal teachers to transfer dark knowledge into 3D representation learning.