Copertina

SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gu, Bo, Zhang, Zhikang, Wei, Zizhuang, Chen, Zhenyuan, Li, Lingyun, Song, Zhuoyi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models
di: Zhao, Ruosen, et al.
Pubblicazione: (2025)

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs
di: Chen, Zhenghao, et al.
Pubblicazione: (2026)

Token Entropy Regularization for Multi-modal Antenna Affiliation Identification
di: Chen, Dong, et al.
Pubblicazione: (2026)

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
di: Ouyang, Kun, et al.
Pubblicazione: (2025)

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

Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation
di: Wang, Hengyi, et al.
Pubblicazione: (2026)

SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs
di: Wang, Siting, et al.
Pubblicazione: (2025)

Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind
di: Plizzari, Chiara, et al.
Pubblicazione: (2024)

Keep it SymPL: Symbolic Projective Layout for Allocentric Spatial Reasoning in Vision-Language Models
di: Jang, Jaeyun, et al.
Pubblicazione: (2026)

PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
di: Wu, Yixuan, et al.
Pubblicazione: (2025)

SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
di: Alansari, Mohamad, et al.
Pubblicazione: (2026)

LiDAR-based Registration against Georeferenced Models for Globally Consistent Allocentric Maps
di: Quenzel, Jan, et al.
Pubblicazione: (2024)

Concat-ID: Towards Universal Identity-Preserving Video Synthesis
di: Zhong, Yong, et al.
Pubblicazione: (2025)

Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
di: Fang, Bo, et al.
Pubblicazione: (2025)

Spatial Preference Rewarding for MLLMs Spatial Understanding
di: Qiu, Han, et al.
Pubblicazione: (2025)

Towards Long-Form Spatio-Temporal Video Grounding
di: Gu, Xin, et al.
Pubblicazione: (2026)

Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
di: Zhu, Rui, et al.
Pubblicazione: (2026)

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
di: Li, Yunheng, et al.
Pubblicazione: (2026)

Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs
di: Tasnim, Nazia, et al.
Pubblicazione: (2025)

SpatialTree: How Spatial Abilities Branch Out in MLLMs
di: Xiao, Yuxi, et al.
Pubblicazione: (2025)

STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
di: Li, Yun, et al.
Pubblicazione: (2025)

GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation
di: Li, Rang, et al.
Pubblicazione: (2025)

Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs
di: Huang, Jincai, et al.
Pubblicazione: (2026)

CodePercept: Code-Grounded Visual STEM Perception for MLLMs
di: Guan, Tongkun, et al.
Pubblicazione: (2026)

Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs Supplementary
di: Tasnim, Nazia, et al.
Pubblicazione: (2026)

Exploring the Design Space of Visual Context Representation in Video MLLMs
di: Du, Yifan, et al.
Pubblicazione: (2024)

Unified Representation Space for 3D Visual Grounding
di: Zheng, Yinuo, et al.
Pubblicazione: (2025)

Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition
di: Zhang, Xiaoying, et al.
Pubblicazione: (2025)

DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs
di: Zhao, Jiahe, et al.
Pubblicazione: (2025)

Are Image-to-Video Models Good Zero-Shot Image Editors?
di: Zhang, Zechuan, et al.
Pubblicazione: (2025)

OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding
di: Yao, Jiali, et al.
Pubblicazione: (2025)

RPBG: Towards Robust Neural Point-based Graphics in the Wild
di: Zhu, Qingtian, et al.
Pubblicazione: (2024)

The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs
di: Anvekar, Tejas, et al.
Pubblicazione: (2025)

RieMind: Geometry-Grounded Spatial Agent for Scene Understanding
di: Ropero, Fernando, et al.
Pubblicazione: (2026)

Video-R1: Reinforcing Video Reasoning in MLLMs
di: Feng, Kaituo, et al.
Pubblicazione: (2025)

Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
di: Liu, Shizhan, et al.
Pubblicazione: (2025)

Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs
di: Zhu, Fangrui, et al.
Pubblicazione: (2025)

Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
di: Zhang, Bob, et al.
Pubblicazione: (2025)

Multi-sentence Video Grounding for Long Video Generation
di: Feng, Wei, et al.
Pubblicazione: (2024)

InstrAct: Towards Action-Centric Understanding in Instructional Videos
di: Yang, Zhuoyi, et al.
Pubblicazione: (2026)