Cover Image

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Qian, Sikarwar, Ankur, Le, Huy, Zhang, Le, Shi, Zhuan, Taslakian, Perouz, Agrawal, Aishwarya
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Communicating about Space: Language-Mediated Spatial Integration Across Partial Views
by: Sikarwar, Ankur, et al.
Published: (2026)

Assessing and Learning Alignment of Unimodal Vision and Language Models
by: Zhang, Le, et al.
Published: (2024)

SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning
by: Li, Yian, et al.
Published: (2026)

Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
by: Zhang, Le, et al.
Published: (2023)

Scope: Selective Cross-modal Orchestration of Visual Perception Experts
by: Zhang, Tianyu, et al.
Published: (2025)

Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering
by: Awal, Rabiul, et al.
Published: (2023)

WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
by: Awal, Rabiul, et al.
Published: (2025)

RiT: Vanilla Diffusion Transformers Suffice in Representation Space
by: Zhang, Le, et al.
Published: (2026)

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
by: Chen, Zhangquan, et al.
Published: (2025)

VisMin: Visual Minimal-Change Understanding
by: Awal, Rabiul, et al.
Published: (2024)

From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs
by: Zhang, Le, et al.
Published: (2026)

UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning
by: Le, Huy, et al.
Published: (2025)

Learning to See the Elephant in the Room: Self-Supervised Context Reasoning in Humans and AI
by: Liu, Xiao, et al.
Published: (2022)

Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison
by: Yang, Qian, et al.
Published: (2024)

ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning
by: Tao, Xingjian, et al.
Published: (2026)

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
by: Nayak, Shravan, et al.
Published: (2025)

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
by: Li, Chengzu, et al.
Published: (2025)

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
by: Zhang, Tianyu, et al.
Published: (2024)

Learning Multi-View Spatial Reasoning from Cross-View Relations
by: Jeong, Suchae, et al.
Published: (2026)

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
by: Wang, Suyuchen, et al.
Published: (2025)

Multimodal Contextualized Support for Enhancing Video Retrieval System
by: Nguyen-Le, Quoc-Bao, et al.
Published: (2024)

Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search
by: Zhang, Jingdong, et al.
Published: (2026)

Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection
by: Chandhok, Shivam, et al.
Published: (2025)

The Promise of RL for Autoregressive Image Editing
by: Ahmadi, Saba, et al.
Published: (2025)

Visual Agentic AI for Spatial Reasoning with a Dynamic API
by: Marsili, Damiano, et al.
Published: (2025)

When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
by: Yu, Shoubin, et al.
Published: (2026)

Enhancing Spatial Reasoning through Visual and Textual Thinking
by: Liang, Xun, et al.
Published: (2025)

MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement
by: Wu, Le, et al.
Published: (2026)

Autonomous Imagination: Closed-Loop Decomposition of Visual-to-Textual Conversion in Visual Reasoning for Multimodal Large Language Models
by: Liu, Jingming, et al.
Published: (2024)

Explaining How Visual, Textual and Multimodal Encoders Share Concepts
by: Cornet, Clément, et al.
Published: (2025)

Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models
by: Zhan, Yufei, et al.
Published: (2025)

Beyond Medical Diagnostics: How Medical Multimodal Large Language Models Think in Space
by: Trinh, Quoc-Huy, et al.
Published: (2026)

What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning
by: Zhou, Yujin, et al.
Published: (2026)

Think3D: Thinking with Space for Spatial Reasoning
by: Zhang, Zaibin, et al.
Published: (2026)

Imagine with the Teacher: Complete Shape in a Multi-View Distillation Way
by: Luo, Zhanpeng, et al.
Published: (2025)

Thinking with Programming Vision: Towards a Unified View for Thinking with Images
by: Guo, Zirun, et al.
Published: (2025)

A Unified View of Abstract Visual Reasoning Problems
by: Małkiński, Mikołaj, et al.
Published: (2024)

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
by: Wu, Junfei, et al.
Published: (2025)

DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localization
by: Liu, Tao, et al.
Published: (2025)

Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence
by: Zhang, Yanbing, et al.
Published: (2026)