CORTEXA
← Browse
arxivcs.CV2026-06-30

Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning

Yuxiang Xie, Qi Lv, Jianming Xing, Zijian Hong, Xiang Deng, Weili Guan, Liqiang Nie

Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpatialBrain, our submission to the RoboSpatial Challenge at the Embodied Reasoning in Action Workshop, CVPR 2026, built on RoboBrain2.5-8B-NV. RoboSpatialBrain combines two training-free, inference-time mechanisms: a forced <think> prefix activation strategy paired with a task-specific post-prompt that elicits deliberate reasoning on context and compatibility tasks, and an explicit reference-frame redirection pipeline that resolves camera-centric and object-centric ambiguity for context tasks. We additionally explore fine-tuning RoboBrain2.5 on compatibility data and present a detailed analysis of its interaction with prompting. RoboSpatialBrain achieved first place in the RoboSpatial Challenge, with an overall success rate of 80.9\% on RoboSpatial-Home. Code is available at https://github.com/YuxiangXie2003/RoboSpatialBrain.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-13

Technical Report on the CVPR 2026@AdvML Workshop Challenge

Tianyuan Zhang, Zonglei Jing, Jiangfan Liu, Ligong Zhang, Ke Ma, Chengzhi Sun, et al.

Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Challenge on adversarial multimodal attacks against autonomous-driving VLAs. Built on DriveLM-style mul…

View free PDFSource page
arxivcs.CV2026-07-01

OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping

Xudong Li, Mengdan Zhang, Peixian Chen, Jiaxi Tan, Zihao Huang, Jingyuan Zheng, et al.

Spatial intelligence remains a persistent challenge for Multimodal Large Language Models (MLLMs), as it requires coherent spatial scene representations beyond basic object recognition. Existing methods typically build such representations through textual reasoning or 3D reconstru…

View free PDFSource page
arxivcs.CV2026-07-06

Reference-Induced Consensus for Selective Posed-Reference Visual Localization

Wonseok Kang, Jaehyun Kim, Jeongmin Lee, Tae-Wan Kim

We present RIC-Loc (Reference-Induced Consensus localization), a scene-training-free posed-reference localizer that is SfM-point-map-free in its main estimator: it uses known reference poses, but not precomputed SfM 3D map points, query-to-map 2D-3D matches, or query-to-map PnP.…

View free PDFSource page
arxivcs.CVcs.AIcs.LGcs.MM2026-06-28

ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models

Rahul Chowdhury, Timothy A Rupprecht, Xuan Shen, Pu Zhao, Yanzhi Wang

Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substantial additional parameters. Our preliminary analysis reveals that rescaling activations in selected transformer layers-without modi…

View free PDFSource page
arxivcs.AIcs.CVcs.MM2026-07-20

OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment

Wenxiao Fan, Hang Yin, Kan Li

Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation. In particular, they often rely on camera-centric cues rather than reasoning from the reference object's viewpoint, leading to systematic errors in non-camera r…

View free PDFSource page
arxivcs.CVcs.AI2026-07-03

R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables

Maxwell Horton, Wei Lu, Quan Tran, Yury Astashonok, Kirmani Ahmed, Babak Damavandi, et al.

Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmarks do not reflect the challenges of handling (1) natural egocentric video, (2) posed RGB-D video inputs, and (3) challenging quanti…

View free PDFSource page