Cover Image

SpatialTree: How Spatial Abilities Branch Out in MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiao, Yuxi, Li, Longfei, Yan, Shen, Liu, Xinhang, Peng, Sida, Wei, Yunchao, Zhou, Xiaowei, Kang, Bingyi
Format:	Preprint
Published:	2025
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

SpatialTracker: Tracking Any 2D Pixels in 3D Space
by: Xiao, Yuxi, et al.
Published: (2024)

SpatialTrackerV2: 3D Point Tracking Made Easy
by: Xiao, Yuxi, et al.
Published: (2025)

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

ERNet: Efficient Non-Rigid Registration Network for Point Sequences
by: He, Guangzhao, et al.
Published: (2025)

Explore How to Inject Beneficial Noise in MLLMs
by: Zhu, Ruishu, et al.
Published: (2025)

Trace Anything: Representing Any Video in 4D via Trajectory Fields
by: Liu, Xinhang, et al.
Published: (2025)

3D Spatial Understanding in MLLMs: Disambiguation and Evaluation
by: Chang, Chun-Peng, et al.
Published: (2024)

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

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
by: Lin, Haotong, et al.
Published: (2024)

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

Revisiting MLLMs: An In-Depth Analysis of Image Classification Abilities
by: Liu, Huan, et al.
Published: (2024)

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

VideoWorld 2: Learning Transferable Knowledge from Real-world Videos
by: Ren, Zhongwei, et al.
Published: (2026)

4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency
by: Yin, Yuyang, et al.
Published: (2023)

SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs
by: Gu, Bo, et al.
Published: (2026)

Agentic 3D Scene Generation with Spatially Contextualized VLMs
by: Liu, Xinhang, et al.
Published: (2025)

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
by: Ren, Zhongwei, et al.
Published: (2025)

Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
by: Wang, Yifan, et al.
Published: (2024)

ACTRESS: Active Retraining for Semi-supervised Visual Grounding
by: Kang, Weitai, et al.
Published: (2024)

See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning
by: Wei, Yuxi, et al.
Published: (2026)

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

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

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

SAM-guided Graph Cut for 3D Instance Segmentation
by: Guo, Haoyu, et al.
Published: (2023)

MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training
by: He, Xingyi, et al.
Published: (2025)

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
by: Wang, Wei, et al.
Published: (2026)

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

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

LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
by: Lou, Haoran, et al.
Published: (2025)

Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans
by: Qiu, Yansheng, et al.
Published: (2025)

Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling
by: Chen, Xuhai, et al.
Published: (2026)

UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction
by: Cao, Jin, et al.
Published: (2025)

IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation
by: Yu, Xiao, et al.
Published: (2025)

Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation
by: Cen, Zhi, et al.
Published: (2025)

Generating Human Motion in 3D Scenes from Text Descriptions
by: Cen, Zhi, et al.
Published: (2024)

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

Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature Aggregation
by: Qian, Shun, et al.
Published: (2024)

APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
by: Hong, Minjie, et al.
Published: (2025)

Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames
by: Ravi, Sahithya, et al.
Published: (2025)

Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion
by: Jiang, QingYuan, et al.
Published: (2025)