Related papers: Language-to-Space Programming for Training-Free 3D…

Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding and reasoning tasks. We attribute this gap to the absence of a visual geometry learning process capable of…

Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive little to no attention in the final layers of the LLM module of VLMs from the answer tokens,…

Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial interactions. We present a novel approach to address this gap by translating physical-world…

With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning capabilities, enabling them to address a wide range of complex problems. Inspired by these…

Understanding and reasoning about complex 3D environments requires structured scene representations that capture not only objects but also their semantic and spatial relationships. While recent works on 3D scene graph generation have…

Recent works have shown that Large Language Models (LLMs) can be applied to ground natural language to a wide variety of robot skills. However, in practice, learning multi-task, language-conditioned robotic skills typically requires…

Modern 3D object detection datasets are constrained by narrow class taxonomies and costly manual annotations, limiting their ability to scale to open-world settings. In contrast, 2D vision-language models trained on web-scale image-text…

Despite recent advances on multi-modal models, 3D spatial reasoning remains a challenging task for state-of-the-art open-source and proprietary models. Recent studies explore data-driven approaches and achieve enhanced spatial reasoning…

Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation in the form of reasoning and planning. Despite the progress, most still rely on pre-defined motion primitives to…

Real-world applications, such as autonomous driving and humanoid robot manipulation, require precise spatial perception. However, it remains underexplored how Vision-Language Models (VLMs) recognize spatial relationships and perceive…

Vision-language models (VLMs) have achieved strong performance in multimodal understanding and reasoning, yet grounded reasoning in 3D scenes remains underexplored. Effective 3D reasoning hinges on accurate grounding: to answer open-ended…

Zero-shot 3D Visual Grounding (3DVG) is a critical capability for open-world embodied AI. However, existing methods are fundamentally bottlenecked by the poor quality of open-vocabulary 3D proposals, suffering from inaccurate categories and…

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…

Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial…

Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, e.g., in the…

While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a…

Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data…

Humans naturally possess the spatial reasoning ability to form and manipulate images and structures of objects in space. There is an increasing effort to endow Vision-Language Models (VLMs) with similar spatial reasoning capabilities.…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

We present lazy visual grounding, a two-stage approach of unsupervised object mask discovery followed by object grounding, for open-vocabulary semantic segmentation. Plenty of the previous art casts this task as pixel-to-text classification…