paper-with-me

Papers

SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning

2026-04-19 · Yian Li, Yang Jiao, Bin Zhu, Tianwen Qian, Shaoxiang Chen, Jingjing Chen, Yu-Gang Jiang arxiv

Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal large language models (MLLMs) often exhibit fragile reasoning traces in spatial intelligence tasks that involve consistent spatial state recognition. We argue that these failures stem from a mismatch between the spatial recognition mechanism and the text-only reasoning behavior of these MLLMs. Effective spatial reasoning requires low-level geometric structure to be faithfully preserved and updated throughout the reasoning process, whereas textual representations tend to abstract away precisely these critical details. To address this issue, we propose SpatialImaginer, a unified multimodal generation framework that integrates textual reasoning with visual imagination. Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation. To support this capability, we further introduce a difficulty-aware data engine with closed-loop verification to train the model to invoke visual imagination selectively when stable spatial state tracking is required. Extensive experiments on diverse spatial intelligence benchmarks show that SpatialImaginer achieves state-of-the-art performance and substantially improves robustness on complex multi-step spatial reasoning tasks.

📄 PDF Abstract BibTeX arXiv:2604.17385

Code (0)

등록된 구현이 없습니다.

Tasks

multimodal generationSpatial Reasoning

Similar Papers 제목 키워드 기반

When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning

2026-02-09 · Shoubin Yu, Yue Zhang, Zun Wang, Jaehong Yoon 외 arxiv

Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under unseen or alternative viewpoints. Recent work addresses this by augmenting reason…

Spatial Reasoning

Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators

2026-06-04 · Chenming Zhu, Jingli Lin, Yilin Long, Peizhou Cao 외 arxiv

While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the observed images and text-oriented chain-of-thought. They often stru…

Spatial ReasoningVisual Reasoning

ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination

2025-12-19 · Teng Wang, Xinxin Zhao, Wenzhe Cai, Changyin Sun arxiv

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 comm…

Spatial ReasoningVisual Navigation

Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling

2025-12-01 · Meng Cao, Haokun Lin, Haoyuan Li, Haoran Tang 외 arxiv

Spatial reasoning, the ability to understand and interpret the 3D structure of the world, is a critical yet underdeveloped capability in Multimodal Large Language Models (MLLMs). Current methods predominantly rely on ver…

Spatial Reasoning

CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming

2026-06-21 · Ruixun Liu, Lingyu Zhang, Lanxuan Xue, Kaiyu Li 외 arxiv

Humans can effortlessly reason about scenes across different viewpoints, yet it remains unclear whether Vision-Language Models (VLMs) possess similar cross-view spatial abilities. Satellite-street scene pairs, with their…

Spatial Reasoning