Related papers: CLTP: Contrastive Language-Tactile Pre-training fo…

The ambiguity of human emotions poses several challenges for machine learning models, as they often overlap and lack clear delineating boundaries. Contrastive language-audio pretraining (CLAP) has emerged as a key technique for…

Physical reasoning is important for effective robot manipulation. Recent work has investigated both vision and language modalities for physical reasoning; vision can reveal information about objects in the environment and language serves as…

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between…

Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this…

Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the learning in 3D scene understanding has yet to be explored.…

A 3D scene graph represents a compact scene model by capturing both the objects present and the semantic relationships between them, making it a promising structure for robotic applications. To effectively interact with users, an embodied…

In this work, we present Uni3DL, a unified model for 3D and Language understanding. Distinct from existing unified vision-language models in 3D which are limited in task variety and predominantly dependent on projected multi-view images,…

Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions). While this is useful for matching images to natural…

We introduce ChatPose, a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated by the human ability to intuitively understand postures from…

This paper proposes Comprehensive Pathology Language Image Pre-training (CPLIP), a new unsupervised technique designed to enhance the alignment of images and text in histopathology for tasks such as classification and segmentation. This…

As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a…

Vision-Language-Action (VLA) models have demonstrated significant advantages in robotic manipulation. However, their reliance on vision and language often leads to suboptimal performance in tasks involving visual occlusion, fine-grained…

Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…

Multi-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes. In addition to being memory-efficient, multi-task models, when appropriately designed, can facilitate the exchange of…

Large language models (LLMs) are beginning to automate reward design for dexterous manipulation. However, no prior work has considered tactile sensing, which is known to be critical for human-like dexterity. We present Text2Touch, bringing…

Vision-language models (VLMs) have demonstrated strong cross-modal capabilities, yet most work remains limited to 2D data and assumes binary supervision (i.e., positive vs. negative pairs), overlooking the continuous and structured…

Recent research has demonstrated that Large Language Models (LLMs) are not limited to text-only tasks but can also function as multimodal models across various modalities, including audio, images, and videos. In particular, research on 3D…

This paper highlights a shift in how to approach material generation. Instead of material-to-material, we propose a language-to-material generation architecture that utilizes millions of untapped data points. Using a web scraper to collect…

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information…

Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning.…