Imagen de Portada

World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Wanyue, Wu, Wenxiang, Xu, Wang, Luo, Jiaxin, Zhi, Helu, Huang, Yibin, Ren, Shuo, Liu, Zitao, Zhang, Jiajun
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
por: Zhang, Wanyue, et al.
Publicado: (2025)

Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning
por: Huang, Yibin, et al.
Publicado: (2025)

Thinking with Spatial Code for Physical-World Video Reasoning
por: Chen, Jieneng, et al.
Publicado: (2026)

Can World Models Benefit VLMs for World Dynamics?
por: Zhang, Kevin, et al.
Publicado: (2025)

HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs
por: Zhang, Zijian, et al.
Publicado: (2025)

WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning
por: Englmeier, Stefan, et al.
Publicado: (2026)

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
por: Cao, Jiajun, et al.
Publicado: (2025)

Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World
por: Huang, Yuzhi, et al.
Publicado: (2026)

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
por: Li, Jiangyang, et al.
Publicado: (2026)

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

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

PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models
por: Mak, Chak-Wing, et al.
Publicado: (2026)

Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling
por: Cao, Meng, et al.
Publicado: (2025)

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs
por: Zhang, Xintong, et al.
Publicado: (2025)

WPT: World-to-Policy Transfer via Online World Model Distillation
por: Jiang, Guangfeng, et al.
Publicado: (2025)

Choreographing a World of Dynamic Objects
por: Lyu, Yanzhe, et al.
Publicado: (2026)

GeoWorld-VLM: Geometry from World Models for Vision-Language Models
por: Gu, Renjie, et al.
Publicado: (2026)

From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs
por: Wu, Mingrui, et al.
Publicado: (2025)

VISTAv2: World Imagination for Indoor Vision-and-Language Navigation
por: Huang, Yanjia, et al.
Publicado: (2025)

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
por: Shen, Yifan, et al.
Publicado: (2025)

WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation
por: Zhang, Daoan, et al.
Publicado: (2025)

SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
por: Zhang, Jian, et al.
Publicado: (2026)

Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
por: Ma, Xueqi, et al.
Publicado: (2026)

MyVLM: Personalizing VLMs for User-Specific Queries
por: Alaluf, Yuval, et al.
Publicado: (2024)

CLGRPO: Reasoning Ability Enhancement for Small VLMs
por: Wang, Fanyi, et al.
Publicado: (2025)

MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control
por: Zhou, Enshen, et al.
Publicado: (2024)

SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks
por: Song, Zijian, et al.
Publicado: (2025)

SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs
por: Zhang, Yuyou, et al.
Publicado: (2025)

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning
por: Zhou, Heng, et al.
Publicado: (2026)

Linear Scaling Video VLMs for Long Video Understanding
por: Eyzaguirre, Cristobal, et al.
Publicado: (2026)

An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identification
por: Zhang, Lei, et al.
Publicado: (2024)

VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition
por: Zhang, Zaiwei, et al.
Publicado: (2024)

Jigsaw++: Imagining Complete Shape Priors for Object Reassembly
por: Lu, Jiaxin, et al.
Publicado: (2024)

DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry
por: Wu, Changti, et al.
Publicado: (2025)

MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
por: Pan, Zhenyu, et al.
Publicado: (2025)

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
por: Wang, Yuxin, et al.
Publicado: (2025)

What if? Emulative Simulation with World Models for Situated Reasoning
por: Liu, Ruiping, et al.
Publicado: (2026)

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
por: Wang, Dianyi, et al.
Publicado: (2026)

Reasoning in Space via Grounding in the World
por: Chen, Yiming, et al.
Publicado: (2025)

Audio-Visual World Models: Towards Multisensory Imagination in Sight and Sound
por: Wang, Jiahua, et al.
Publicado: (2025)