Related papers: Reasoning Matters for 3D Visual Grounding

3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning, yet many rely on a single pointer-style grounding decision…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

In this paper, we claim that 3D visual grounding is the cornerstone of spatial reasoning and introduce the Grounded-Spatial Reasoner (GS-Reasoner) to explore the effective spatial representations that bridge the gap between them. Existing…

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual…

The increasing demand for intelligent systems capable of interpreting and reasoning about visual content requires the development of large Vision-and-Language Models (VLMs) that are not only accurate but also have explicit reasoning…

Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in…

Vision-language models (VLMs) have achieved remarkable success in scene understanding and perception tasks, enabling robots to plan and execute actions adaptively in dynamic environments. However, most multimodal large language models lack…

Large vision-and-language models (VLMs) trained to match images with text on large-scale datasets of image-text pairs have shown impressive generalization ability on several vision and language tasks. Several recent works, however, showed…

3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, zero-shot 3DVG holds greater promise for real-world…

Learning to ground natural language queries to target objects or regions in 3D point clouds is quite essential for 3D scene understanding. Nevertheless, existing 3D visual grounding approaches require a substantial number of bounding box…

Recent progress in medical vision-language models (VLMs) has achieved strong performance on image-level text-centric tasks such as report generation and visual question answering (VQA). However, achieving fine-grained visual grounding and…

As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods…

Currently, utilizing large language models to understand the 3D world is becoming popular. Yet existing 3D-aware LLMs act as black boxes: they output bounding boxes or textual answers without revealing how those decisions are made, and they…

Visual grounding is an essential capability of Visual Language Models (VLMs) to understand the real physical world. Previous state-of-the-art grounding visual language models usually have large model sizes, making them heavy for deployment…

Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a…

Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. However, existing \VLMs{}'…

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial intelligence. Nevertheless, achieving deep spatial…

Prompt-driven scene synthesis allows users to generate complete 3D environments from textual descriptions. Current text-to-scene methods often struggle with complex geometries and object transformations, and tend to show weak adherence to…

Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special…

Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…