相关论文: SOTA: Self-adaptive Optimal Transport for Zero-Sho…

Source Free Unsupervised Domain Adaptation (SFUDA) is critical for deploying deep learning models across diverse clinical settings. However, existing methods are typically designed for low-gap, specific domain shifts and cannot generalize…

We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objects are always visible, leading to brittle and reactive…

Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In…

Few-shot adaptation of vision-language models (VLMs) like CLIP typically relies on learning textual prompts matched to global image embeddings. Recent works extend this paradigm by incorporating local image-text alignment to capture…

The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their pre-training objectives. For instance,…

In autonomous driving, it is crucial to correctly interpret traffic gestures (TGs), such as those of an authority figure providing orders or instructions, or a pedestrian signaling the driver, to ensure a safe and pleasant traffic…

With the emergence of transformer-based architectures and large language models (LLMs), the accuracy of road scene perception has substantially advanced. Nonetheless, current road scene segmentation approaches are predominantly trained on…

Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains. To enhance CLIP's performance while preserving the zero-shot paradigm, various…

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

Foundation Models (FMs) have demonstrated unprecedented capabilities including zero-shot learning, high fidelity data synthesis, and out of domain generalization. However, as we show in this paper, FMs still have poor out-of-the-box…

LiDAR-based world models offer more structured and geometry-aware representations than their image-based counterparts. However, existing LiDAR world models are narrowly trained; each model excels only in the domain for which it was built.…

The emergence of multi-modal foundation models has markedly transformed the technology for autonomous driving, shifting away from conventional and mostly hand-crafted design choices towards unified, foundation-model-based approaches,…

Visual foundation models (VFMs) have become increasingly popular due to their state-of-the-art performance. However, interpretability remains crucial for critical applications. In this sense, self-explainable models (SEM) aim to provide…

With the increasing attention to large vision-language models such as CLIP, there has been a significant amount of effort dedicated to building efficient prompts. Unlike conventional methods of only learning one single prompt, we propose to…

Large pretrained (e.g., "foundation") models exhibit distinct capabilities depending on the domain of data they are trained on. While these domains are generic, they may only barely overlap. For example, visual-language models (VLMs) are…

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and…

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicability to embodied systems. As a result, recent work…

Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing…

Autonomous navigation under natural language instructions represents a crucial step toward embodied intelligence, enabling complex task execution in environments ranging from industrial facilities to domestic spaces. However,…