相关论文: MosaicThinker: On-Device Visual Spatial Reasoning …

This study focuses on Embodied Complex-Question Answering task, which means the embodied robot need to understand human questions with intricate structures and abstract semantics. The core of this task lies in making appropriate plans based…

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…

Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large Language Models (LLMs) to incorporate commonsense reasoning…

Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can…

Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial evidence. Existing benchmarks also evaluate VLMs on isolated…

Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks by combining visual representations with the abstract skill set large language models (LLMs) learn during pretraining. Vision,…

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.…

Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged as a promising ante-hoc approach that provides…

The use of Multimodal Large Language Models (MLLMs) as an end-to-end solution for Embodied AI and Autonomous Driving has become a prevailing trend. While MLLMs have been extensively studied for visual semantic understanding tasks, their…

Vision language models (VLMs) are an exciting emerging class of language models (LMs) that have merged classic LM capabilities with those of image processing systems. However, the ways that these capabilities combine are not always…

Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence into discrete textual thoughts, creating an information bottleneck for fine-grained…

Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The…

Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities, the ability to reason about the physical world, and reactively choose appropriate motor skills. Vision-language models…

The task of video inpainting detection is to expose the pixel-level inpainted regions within a video sequence. Existing methods usually focus on leveraging spatial and temporal inconsistencies. However, these methods typically employ fixed…

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.…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT)…

Recent progress in Vision Language Models (VLMs) has raised the question of whether they can reliably perform nonverbal reasoning. To this end, we introduce VRIQ (Visual Reasoning IQ), a novel benchmark designed to assess and analyze the…

Vision and language understanding has emerged as a subject undergoing intense study in Artificial Intelligence. Among many tasks in this line of research, visual question answering (VQA) has been one of the most successful ones, where the…

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical…