Related papers: SPA: 3D Spatial-Awareness Enables Effective Embodi…

Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and embodied agents. We attribute this to a modality gap between…

Despite the ubiquity of large language models (LLMs) in AI research, the question of embodiment in LLMs remains underexplored, distinguishing them from embodied systems in robotics where sensory perception directly informs physical action.…

A metric-accurate semantic 3D representation is essential for many robotic tasks. This work proposes a simple, yet powerful, way to integrate the 2D embeddings of a Vision-Language Model in a metric-accurate 3D representation at real-time.…

Vision-language models (VLMs) work well in tasks ranging from image captioning to visual question answering (VQA), yet they struggle with spatial reasoning, a key skill for understanding our physical world that humans excel at. We find that…

Recently, transformers have shown great potential in image classification and established state-of-the-art results on the ImageNet benchmark. However, compared to CNNs, transformers converge slowly and are prone to overfitting in low-data…

Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordings such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which…

Holistic understanding and reasoning in 3D scenes are crucial for the success of autonomous driving systems. The evolution of 3D semantic occupancy prediction as a pretraining task for autonomous driving and robotic applications captures…

Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich…

Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. 'head-centred', 'hand-centred' and 'world-based'). Recent advances in reinforcement learning demonstrate a quite different approach…

Spatial reasoning in large-scale 3D environments such as warehouses remains a significant challenge for vision-language systems due to scene clutter, occlusions, and the need for precise spatial understanding. Existing models often struggle…

3D scene graphs have recently emerged as a powerful high-level representation of 3D environments. A 3D scene graph describes the environment as a layered graph where nodes represent spatial concepts at multiple levels of abstraction and…

Learning robust and effective representations of visual data is a fundamental task in computer vision. Traditionally, this is achieved by training models with labeled data which can be expensive to obtain. Self-supervised learning attempts…

Robotic manipulation in 3D requires effective computation of N degree-of-freedom joint-space trajectories that enable precise and robust control. To achieve this, robots must integrate semantic understanding with visual perception to…

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either…

Understanding of spatial attributes is central to effective 3D radiology image analysis where crop-based learning is the de facto standard. Given an image patch, its core spatial properties (e.g., position & orientation) provide helpful…

In the visual spatial understanding (VSU) area, spatial image-to-text (SI2T) and spatial text-to-image (ST2I) are two fundamental tasks that appear in dual form. Existing methods for standalone SI2T or ST2I perform imperfectly in spatial…

To date, various 3D scene understanding tasks still lack practical and generalizable pre-trained models, primarily due to the intricate nature of 3D scene understanding tasks and their immense variations introduced by camera views,…

Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric…

We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation, we repurpose a pretrained 2D diffusion model by extending its self-attention layers with…

Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations…