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

Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring cross-viewpoint understanding and spatial reasoning. We…

Understanding and reasoning about spatial relationships is a fundamental capability for Visual Question Answering (VQA) and robotics. While Vision Language Models (VLM) have demonstrated remarkable performance in certain VQA benchmarks,…

Spatial reasoning remains a fundamental challenge for Vision-Language Models (VLMs), with current approaches struggling to achieve robust performance despite recent advances. We identify that this limitation stems from a critical gap:…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer…

The growing interest in embodied agents increases the demand for spatiotemporal video understanding, yet existing benchmarks largely emphasize extractive reasoning, where answers can be explicitly presented within spatiotemporal events. It…

The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive reasoning. By invoking visual tools or generating intermediate…

Achieving human-like spatial intelligence for vision-language models (VLMs) requires inferring 3D structures from 2D observations, recognizing object properties and relations in 3D space, and performing high-level spatial reasoning. In this…

Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render…

Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…

Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive…

Embodied agents are expected to assist humans by actively exploring unknown environments and reasoning about spatial contexts. When deployed in real life, agents often face sequential tasks where each new task follows the completion of the…

Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We…

Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Medical VLMs often rely…

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…

We present a conceptual framework for training Vision-Language Models (VLMs) to perform Visual Perspective Taking (VPT), a core capability for embodied cognition essential for Human-Robot Interaction (HRI). As a first step toward this goal,…

When large vision-language models are applied to the field of robotics, they encounter problems that are simple for humans yet error-prone for models. Such issues include confusion between third-person and first-person perspectives and a…

Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still…

Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing…

Recent multimodal large language models (MLLMs) have made remarkable progress in visual understanding and language-based reasoning, yet they lack a persistent world-centered representation for spatially consistent reasoning in 3D…