Cover Image

Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Zhongyi, Du, Yi, Wang, Chen, Kong, Yu
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

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
by: Lu, Yiren, et al.
Published: (2026)

3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
by: Yang, Yuncong, et al.
Published: (2024)

Vision-Language Memory for Spatial Reasoning
by: Liu, Zuntao, et al.
Published: (2025)

Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning
by: Chen, Jiahua, et al.
Published: (2026)

GaussExplorer: 3D Gaussian Splatting for Embodied Exploration and Reasoning
by: Yu-Ji, Kim, et al.
Published: (2026)

Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence
by: Zheng, Yufei, et al.
Published: (2026)

Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations
by: Yuan, Jiangye, et al.
Published: (2026)

IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios
by: Li, Yifan, et al.
Published: (2025)

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models
by: Zhang, Jiaxin, et al.
Published: (2026)

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
by: Yang, Ganlin, et al.
Published: (2025)

ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
by: Zhou, Zhongyi, et al.
Published: (2025)

EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision
by: Cao, Yifei, et al.
Published: (2025)

MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation
by: Huang, Jiaxin, et al.
Published: (2025)

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

IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation
by: Li, Yifan, et al.
Published: (2025)

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

S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance
by: Xu, Beining, et al.
Published: (2025)

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
by: Yu, Hanxun, et al.
Published: (2026)

REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian Splatting
by: Shi, Changyue, et al.
Published: (2025)

Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models
by: Zhang, Jiyao, et al.
Published: (2026)

SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
by: Ma, Wufei, et al.
Published: (2025)

Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation
by: Bai, Weimin, et al.
Published: (2025)

GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
by: Liu, Zhaochen, et al.
Published: (2026)

VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
by: Wang, Shaoan, et al.
Published: (2026)

Judge Anything: MLLM as a Judge Across Any Modality
by: Pu, Shu, et al.
Published: (2025)

3D Reconstruction with Spatial Memory
by: Wang, Hengyi, et al.
Published: (2024)

Thinking with Geometry: Active Geometry Integration for Spatial Reasoning
by: Li, Haoyuan, et al.
Published: (2026)

3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering
by: Xu, Rongtao, et al.
Published: (2025)

G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
by: Hu, Wenbo, et al.
Published: (2025)

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
by: Zhu, Ziyu, et al.
Published: (2025)

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
by: Deng, Nianchen, et al.
Published: (2025)

Virgo: A Preliminary Exploration on Reproducing o1-like MLLM
by: Du, Yifan, et al.
Published: (2025)

MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence
by: Yin, Xingyilang, et al.
Published: (2026)

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning
by: He, Jixuan, et al.
Published: (2026)

Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning
by: Zhao, Baining, et al.
Published: (2025)

Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning
by: Huang, Qihan, et al.
Published: (2025)

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
by: Xu, Jingwei, et al.
Published: (2024)

3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark
by: Ma, Wufei, et al.
Published: (2024)

Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning
by: Xu, Huilin, et al.
Published: (2025)

HAMMER: Harnessing MLLM via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding
by: Yao, Lei, et al.
Published: (2026)