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 …

Research on multi-modal learning dominantly aligns the modalities in a unified space at
training, and only a single one is taken for prediction at inference. However, for a real …

Contrastive learning has emerged as a promising paradigm for 3D open-world
understanding ie aligning point cloud representation to image and text embedding space …

Human intelligence, the most evident and accessible form of source of reasoning, hosted by
biological hardware, has evolved and been refined over thousands of years, positioning …

We introduce Duoduo CLIP, a model for 3D representation learning that learns shape
encodings from multi-view images instead of point-clouds. The choice of multi-view images …

Haptic feedback has been integrated into Virtual and Augmented Reality, complementing
acoustic and visual information and contributing to an all-round immersive experience in …

Despite impressive advancements in recent multimodal reasoning approaches, they are still
limited in flexibility and efficiency, as these models typically process only a few fixed …

The trend of employing training-free methods for point cloud recognition is becoming
increasingly popular due to its significant reduction in computational resources and time …

Brain semantic decoding has received a surge of attention in the computer vision and
neuroscience disciplines. However, existing techniques ignore the sparse and implicit …

Visuo-tactile sensors aim to emulate human tactile perception, enabling robots to precisely
understand and manipulate objects. Over time, numerous meticulously designed visuo …