3 accepted papers
Learning multimodal representation is a fundamental task that supports a wide range of applications such as visual-text retrieval. While pioneering approaches e.g., CLIP paves the way by learning separated encoders for different modalities, they struggle to model complex interactions between modalit
Research on 3D Vision-Language Models (3D-VLMs) is gaining increasing attention, which is crucial for developing embodied AI within 3D scenes, such as visual navigation and embodied question answering. Due to the high density of visual features, especially in large 3D scenes, accurately locating tas…
"We study zero-shot instance navigation, in which the agent navigates to a specific object without using object annotations for training. Previous object navigation approaches apply the image-goal navigation () task (go to the location of an image) for pretraining, and transfer the agent to achieve…