arXiv AI By Haibo Wang, Lifu Huang

Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models

Read the original on arXiv AI →

arXiv:2606. 05833v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to maintain geometric and spatial consistency across video frames.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers
Jun 4

Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to maintain geometric and spatial consistency across video frames. Given the scarcity of large-scale 3D data, we present GeoVR, a novel framework that learns geometric representations using purely 2D video sequences.

arXiv AI
Jul 24

3D-Aware VLMs with Implicit and Explicit Geometries

arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.

By Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Ran Xu, Shijian Lu, Gongjie Zhang
arXiv Machine Learning
5d ago

SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models

arXiv:2601. 11729v2 Announce Type: replace-cross Abstract: Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicability to embodied systems.

By Turhan Can Kargin, Wojciech Jasi\'nski, Adam Pardyl, Bartosz Zieli\'nski, Marcin Przewi\k{e}\'zlikowski