Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Recent advancements in multimodal pre-training have shown promising efficacy in 3D
representation learning by aligning multimodal features across 3D shapes their 2D …

We introduce OpenShape, a method for learning multi-modal joint representations of text,
image, and point clouds. We adopt the commonly used multi-modal contrastive learning …

This paper presents DreamLLM, a learning framework that first achieves versatile
Multimodal Large Language Models (MLLMs) empowered with frequently overlooked …

Large language models (LLMs) based on the generative pre-training transformer (GPT)
have demonstrated remarkable effectiveness across a diverse range of downstream tasks …

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image,
language, audio, and video. Guided by ImageBind, we construct a joint embedding space …

Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not
present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has …

Training a 3D scene understanding model requires complicated human annotations, which
are laborious to collect and result in a model only encoding close-set object semantics. In …

Transformers have become one of the foundational architectures in point cloud analysis
tasks due to their excellent global modeling ability. However, the attention mechanism has …

Scaling up representations for images or text has been extensively investigated in the past
few years and has led to revolutions in learning vision and language. However, scalable …