Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Shoubin, Zhang, Yue, Wang, Zun, Yoon, Jaehong, Yao, Huaxiu, Ding, Mingyu, Bansal, Mohit
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
by: Yoon, Jaehong, et al.
Published: (2024)

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion
by: Yu, Shoubin, et al.
Published: (2024)

RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives
by: Yoon, Jaehong, et al.
Published: (2024)

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
by: Wang, Ziyang, et al.
Published: (2025)

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation
by: Yu, Shoubin, et al.
Published: (2025)

AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
by: Wang, Zun, et al.
Published: (2026)

Multimodal Representation Learning by Alternating Unimodal Adaptation
by: Zhang, Xiaohui, et al.
Published: (2023)

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
by: Wang, Ziyang, et al.
Published: (2024)

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
by: Lee, Daeun, et al.
Published: (2026)

Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
by: Lee, Daeun, et al.
Published: (2025)

Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization
by: Li, Jialu, et al.
Published: (2025)

DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation
by: Wang, Zun, et al.
Published: (2024)

EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
by: Wang, Ziyang, et al.
Published: (2026)

STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models
by: Liang, Yiming, et al.
Published: (2026)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
by: Zhang, Yue, et al.
Published: (2026)

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
by: Sung, Yi-Lin, et al.
Published: (2023)

EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
by: Wang, Zun, et al.
Published: (2025)

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

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
by: Zhou, Yiyang, et al.
Published: (2023)

Hierarchy-Aware Multimodal Unlearning for Medical AI
by: Wu, Fengli, et al.
Published: (2025)

Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
by: Lee, Daeun, et al.
Published: (2024)

Planning with Sketch-Guided Verification for Physics-Aware Video Generation
by: Huang, Yidong, et al.
Published: (2025)

DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
by: Sivakumaran, Nithin, et al.
Published: (2025)

SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts
by: Zhou, Gengze, et al.
Published: (2024)

Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
by: Wang, Xiyao, et al.
Published: (2024)

Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution
by: Sivakumaran, Nithin, et al.
Published: (2026)

PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
by: Huang, Yidong, et al.
Published: (2026)

SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
by: Li, Jialu, et al.
Published: (2024)

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents
by: Zala, Abhay, et al.
Published: (2024)

VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation
by: Yu, Shoubin, et al.
Published: (2025)

Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering
by: Frahm, Noah, et al.
Published: (2025)

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
by: Sung, Yi-Lin, et al.
Published: (2025)

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel
by: Wang, Zun, et al.
Published: (2024)

V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
by: Lin, Han, et al.
Published: (2026)

WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
by: Yeo, Woongyeong, et al.
Published: (2025)

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
by: Prasad, Archiki, et al.
Published: (2023)

MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
by: Yang, Yuncong, et al.
Published: (2025)

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
by: Pothiraj, Atin, et al.
Published: (2025)

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning
by: Yang, Qian, et al.
Published: (2026)

STAR: A Benchmark for Situated Reasoning in Real-World Videos
by: Wu, Bo, et al.
Published: (2024)