Related papers: SPAZER: Spatial-Semantic Progressive Reasoning Age…

3D visual grounding (3DVG) aims to localize objects in a 3D scene based on natural language queries. In this work, we explore zero-shot 3DVG from multi-view images alone, without requiring any geometric supervision or object priors. We…

Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source…

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…

Efficient target localization and autonomous navigation in complex environments are fundamental to real-world embodied applications. While recent advances in multimodal foundation models have enabled zero-shot object goal navigation,…

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…

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In…

Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous…

Visual grounding, the task of linking textual queries to specific regions within images, plays a pivotal role in vision-language integration. Existing methods typically rely on extensive task-specific annotations and fine-tuning, limiting…

Visual Language Models (VLMs) have increasingly become the main paradigm for understanding indoor scenes, but they still struggle with metric and spatial reasoning. Current approaches rely on end-to-end video understanding or large-scale…

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…

Object navigation is a core capability of embodied intelligence, enabling an agent to locate target objects in unknown environments. Recent advances in vision-language models (VLMs) have facilitated zero-shot object navigation (ZSON).…

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the…

Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption…

The Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) task requires agents to navigate previously unseen 3D environments using natural language instructions, without any scene-specific training. A critical…

Though recent advances in vision-language models (VLMs) have achieved remarkable progress across a wide range of multimodal tasks, understanding 3D spatial relationships from limited views remains a significant challenge. Previous reasoning…

Visual reasoning -- the ability to interpret the visual world -- is crucial for embodied agents that operate within three-dimensional scenes. Progress in AI has led to vision and language models capable of answering questions from images.…

Language-driven object navigation requires agents to interpret natural language descriptions of target objects, which combine intrinsic and extrinsic attributes for instance recognition and commonsense navigation. Existing methods either…

Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning,…

Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description. However, existing methods only consider the dependency between the entire sentence and the target…

The ability to understand and reason the 3D real world is a crucial milestone towards artificial general intelligence. The current common practice is to finetune Large Language Models (LLMs) with 3D data and texts to enable 3D…