arXiv Computer Vision October 15, 2026 By Qihang Cao, Haoyuan Li, Zihan Guo, Sensen Gao, Zihui Gao, Huixin Zhang, Fan He, Jianhua Han, Hang Xu, Xiaodan Liang, Jia-Wang Bian

DynThinker: Unifying Static 3D and Dynamic 4D Spatial Reasoning

Read the original on arXiv Computer Vision →

The Flow has not summarised this story yet — read it at arXiv Computer Vision.

Hugging Face Trending Papers

5d ago

DynThinker: Unifying Static 3D and Dynamic 4D Spatial Reasoning

Achieving general spatial intelligence requires a unified understanding of both static 3D and dynamic 4D. However, we find that existing models struggle to excel at both: 3D post-training can weaken d...

multimodal benchmarks

arXiv Computer Vision

Aug 26

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models

arXiv:2510.13394v4 Announce Type: replace Abstract: Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, au...

By Xinmiao Huang, Qisong He, Zhenglin Huang, Boxuan Wang, Zhuoyun Li, Guangliang Cheng, Yi Dong, Xiaowei Huang

llms agents robotics multimodal benchmarks

arXiv AI

Jun 17

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

arXiv:2606. 17539v1 Announce Type: cross Abstract: Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging.

By Yatai Ji, An-Chieh Cheng, Yang Fu, Yukang Chen, Han Zhang, Zhaojing Yang, Wei Huang, Ka Chun Cheung, Song Han, Vidya Nariyambut Murali, Pavlo Molchanov, Jan Kautz, Simon See, Hongxu Yin, Ping Luo, Sifei Liu

llms reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Computer Vision

4d ago

GeoThinker-$F$: Endogenous Predictive World Representations for Fast Spatial Intelligence

arXiv:2610.20592v1 Announce Type: new Abstract: Existing geometry-aware Multimodal Large Language Models (MLLMs) increasingly rely on external 3D encoders to provide structural priors, but executing...

By Haoyuan Li, Qihang Cao, Huanyuan Zhou, Xin Hu, Sijia Chen, Zihan Guo, Kun Xiang, Yunshuang Nie, Tao Tang, Xinlong Zheng, Jia-Wang Bian, Xianming Liu, Xiaodan Liang

llms multimodal benchmarks

arXiv Machine Learning

Aug 7

Disentangling 3D Modeling from Spatial Reasoning

arXiv:2608. 05242v1 Announce Type: new Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly acquiring implicit 3D perception and reasoning through large-scale training.

By Haoze Sun, Jiequan Cui, Qingshan Xu, Richang Hong

llms fine-tuning benchmarks safety

arXiv AI

Jun 11

Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning

arXiv:2606. 11719v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs).

By Enhan Zhao, Wei Wu, Yuanrui Zhang, Xueliang Zhao, Di He

llms fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

DynThinker: Unifying Static 3D and Dynamic 4D Spatial Reasoning

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

GeoThinker-$F$: Endogenous Predictive World Representations for Fast Spatial Intelligence

Disentangling 3D Modeling from Spatial Reasoning

Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning