Cover Image

On the Generalization Capacities of MLLMs for Spatial Intelligence

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Gongjie, Li, Wenhao, Qian, Quanhao, Wang, Jiuniu, Zhao, Deli, Lu, Shijian, Xu, Ran
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs
by: Jiang, Xueying, et al.
Published: (2026)

RoboSVG: A Unified Framework for Interactive SVG Generation with Multi-modal Guidance
by: Wang, Jiuniu, et al.
Published: (2025)

Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting
by: Miao, Xingyu, et al.
Published: (2025)

Growing Visual Generative Capacity for Pre-Trained MLLMs
by: Wang, Hanyu, et al.
Published: (2025)

Weight Averaging for Out-of-Distribution Generalization and Few-Shot Domain Adaptation
by: Xu, Shijian
Published: (2025)

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

SELU: Self-Learning Embodied MLLMs in Unknown Environments
by: Li, Boyu, et al.
Published: (2024)

Continual Learning for Generative AI: From LLMs to MLLMs and Beyond
by: Guo, Haiyang, et al.
Published: (2025)

STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
by: Li, Wenhao, et al.
Published: (2026)

H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
by: Li, Wenhao, et al.
Published: (2025)

M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning
by: AI, Inclusion, et al.
Published: (2025)

InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
by: Tang, Lv, et al.
Published: (2026)

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
by: Li, Quanhao, et al.
Published: (2025)

Research on the Spatial Data Intelligent Foundation Model
by: Wang, Shaohua, et al.
Published: (2024)

SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis
by: Tian, Huiyuan, et al.
Published: (2024)

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
by: Yu, Tianyu, et al.
Published: (2025)

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
by: Liu, Fangfu, et al.
Published: (2026)

Fine-tuning MLLMs Without Forgetting Is Easier Than You Think
by: Li, He, et al.
Published: (2026)

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

Generative Adversarial Networks Bridging Art and Machine Intelligence
by: Song, Junhao, et al.
Published: (2025)

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance
by: Li, Quanhao, et al.
Published: (2026)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
by: Li, Quanhao, et al.
Published: (2026)

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
by: Li, Siting, et al.
Published: (2024)

SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
by: Peng, Yibo, et al.
Published: (2026)

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
by: Tang, Feilong, et al.
Published: (2025)

VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RL
by: Park, Kyoungjun, et al.
Published: (2025)

CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer
by: Liu, Yang, et al.
Published: (2025)

2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
by: Zhang, Wenqi, et al.
Published: (2025)

RL makes MLLMs see better than SFT
by: Song, Junha, et al.
Published: (2025)

Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
by: Cai, Zhongang, et al.
Published: (2025)

Parallel Sequence Modeling via Generalized Spatial Propagation Network
by: Wang, Hongjun, et al.
Published: (2025)

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs
by: Han, Tianyang, et al.
Published: (2024)

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

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
by: Dalal, Dwip, et al.
Published: (2025)

Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era
by: Hong, Qiuhe, et al.
Published: (2026)

RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
by: Liu, Ziyu, et al.
Published: (2024)

D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
by: Chang, Shuochen, et al.
Published: (2025)

Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin
by: Wang, Fangyikang, et al.
Published: (2025)

Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs
by: Xu, Xiao, et al.
Published: (2025)

JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
by: Song, Lin, et al.
Published: (2026)