Imagen de Portada

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Wei, Yuan, Yuqian, Lin, Tianwei, Zhang, Wenqiao, Tang, Siliang, Xiao, Jun, Zhuang, Yueting
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CrossView-GS: Cross-view Gaussian Splatting For Large-scale Scene Reconstruction
por: Zhang, Chenhao, et al.
Publicado: (2025)

InstructSAM: Segment Any Instance with Any Instructions
por: Yuan, Yuqian, et al.
Publicado: (2026)

Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales
por: Gao, Minghe, et al.
Publicado: (2024)

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
por: Yuan, Yuqian, et al.
Publicado: (2025)

EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs
por: Dai, Yang, et al.
Publicado: (2026)

Robust Modality-incomplete Anomaly Detection: A Modality-instructive Framework with Benchmark
por: Miao, Bingchen, et al.
Publicado: (2024)

EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model
por: Li, Sijing, et al.
Publicado: (2025)

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
por: Yuan, Yuqian, et al.
Publicado: (2024)

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
por: Lin, Tianwei, et al.
Publicado: (2025)

SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion Models
por: Zheng, Haoyu, et al.
Publicado: (2025)

SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness
por: Qiu, Haiyi, et al.
Publicado: (2026)

GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection
por: Dai, Guangyu, et al.
Publicado: (2025)

AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization
por: Yu, Binhe, et al.
Publicado: (2025)

CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
por: Wang, Keyu, et al.
Publicado: (2026)

VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
por: Gao, Mingjian, et al.
Publicado: (2026)

Unified Personalized Understanding, Generating and Editing
por: Zhong, Yu, et al.
Publicado: (2026)

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback
por: Gao, Minghe, et al.
Publicado: (2023)

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
por: Li, Juncheng, et al.
Publicado: (2023)

ICG-MVSNet: Learning Intra-view and Cross-view Relationships for Guidance in Multi-View Stereo
por: Hu, Yuxi, et al.
Publicado: (2025)

T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
por: Yin, Aoxiong, et al.
Publicado: (2024)

Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs
por: Dai, Yang, et al.
Publicado: (2025)

Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
por: Ge, Zhiqi, et al.
Publicado: (2024)

Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness
por: Yu, Qifan, et al.
Publicado: (2024)

LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation
por: Zheng, Haoyu, et al.
Publicado: (2024)

LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation
por: Yuan, Yuqian, et al.
Publicado: (2026)

XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesis
por: Li, Hao, et al.
Publicado: (2024)

MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation
por: Zheng, Haoyu, et al.
Publicado: (2024)

HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
por: Zhang, Wenqiao, et al.
Publicado: (2024)

OpenView: Empowering MLLMs with Out-of-view VQA
por: Chen, Qixiang, et al.
Publicado: (2025)

Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis
por: Lin, Tao Jun, et al.
Publicado: (2024)

Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
por: Fan, Zhaoyu, et al.
Publicado: (2025)

Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting
por: Wang, Weiquan, et al.
Publicado: (2025)

InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
por: Qin, Bosheng, et al.
Publicado: (2023)

MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
por: Kristoffersen, Oskar, et al.
Publicado: (2025)

CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis
por: Li, Weijia, et al.
Publicado: (2024)

OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
por: Bu, Wendong, et al.
Publicado: (2025)

Enhancing Post-Training Quantization via Future Activation Awareness
por: Lv, Zheqi, et al.
Publicado: (2026)

Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program
por: Gao, Minghe, et al.
Publicado: (2025)

Cross-view Localization and Synthesis -- Datasets, Challenges and Opportunities
por: Xu, Ningli, et al.
Publicado: (2025)

On the Generalization Capacities of MLLMs for Spatial Intelligence
por: Zhang, Gongjie, et al.
Publicado: (2026)