Related papers: 3D Vision and Language Pretraining with Large-Scal…

Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising results, most existing methods follow the conventional 2D pipeline in VLMs and use…

With the burgeoning amount of data of image-text pairs and diversity of Vision-and-Language (V\&L) tasks, scholars have introduced an abundance of deep learning models in this research domain. Furthermore, in recent years, transfer learning…

Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs.…

With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes rapid progress. However, limited by existing datasets,…

Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot open vocabulary reasoning over (almost arbitrary) natural…

The advancement of 3D vision-language (3D VL) learning is hindered by several limitations in existing 3D VL datasets: they rarely necessitate reasoning beyond a close range of objects in single viewpoint, and annotations often link…

Vision-language pre-training (VLP) offers unique advantages for surgery by aligning language with surgical videos, enabling workflow understanding and transfer across tasks without relying on expert-labeled datasets. However, progress in…

Vision-language models (VLMs), serve as foundation models for multi-modal applications such as image captioning and text-to-image generation. Recent studies have highlighted limitations in VLM text encoders, particularly in areas like…

Medical Vision Language Pretraining (VLP) has recently emerged as a promising solution to the scarcity of labeled data in the medical domain. By leveraging paired/unpaired vision and text datasets through self-supervised learning, models…

Recent advances in scene understanding have leveraged multimodal large language models (MLLMs) for 3D reasoning by capitalizing on their strong 2D pretraining. However, the lack of explicit 3D data during MLLM pretraining limits 3D…

Vision-Language-Action (VLA) models excel at robotic tasks by leveraging large-scale 2D vision-language pretraining, but their reliance on RGB images limits spatial reasoning critical for real-world interaction. Retraining these models with…

Vision-language navigation (VLN) requires an agent to navigate through an 3D environment based on visual observations and natural language instructions. It is clear that the pivotal factor for successful navigation lies in the comprehensive…

3D Multi-modal Large Language Models (MLLMs) still lag behind their 2D peers, largely because large-scale, high-quality 3D scene-dialogue datasets remain scarce. Prior efforts hinge on expensive human annotation and leave two key…

Synthesizing interactive 3D scenes from text is essential for gaming, virtual reality, and embodied AI. However, existing methods face several challenges. Learning-based approaches depend on small-scale indoor datasets, limiting the scene…

We study the problem of synthesizing immersive 3D indoor scenes from one or more images. Our aim is to generate high-resolution images and videos from novel viewpoints, including viewpoints that extrapolate far beyond the input images while…

The 3D visual grounding task has been explored with visual and language streams comprehending referential language to identify target objects in 3D scenes. However, most existing methods devote the visual stream to capturing the 3D visual…

General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

Embodied task planning demands vision-language models to generate action sequences that are both visually grounded and causally coherent over time. However, existing training paradigms face a critical trade-off: joint end-to-end training…

While multi-modality large language models excel in object-centric or indoor scenarios, scaling them to 3D city-scale environments remains a formidable challenge. To bridge this gap, we propose 3DCity-LLM, a unified framework designed for…