• VGGT-CAD: Reconstructing Parametric CAD 3D Model with Geometric Grounding Chunan Yu, Tianrun Chen, Fu Shen, et al. · arXiv:2609.21225
• Benchmarking World Models for Continual Learning on Compositional Tasks Haoyu Zhou, Joe Watson, Anson Lei, et al. · arXiv:2609.22055
• How unconstrained machine-learning models learn physical symmetries M. Domina, Joseph W Abbott, Paolo Pegolo, et al. · arXiv:2603.24638
• INTCORT: Training-Free Spatial Reasoning Enhancement for Vision-Language Models via Input Transformations and Confidence Routing Haoran Sun, Jingqi Xu, Yanhui Li, et al. · arXiv:2609.24813
• Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World Kaixiang Yao, Xu Wang, Miao Pan, et al. · arXiv:2609.23038
• Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling Xi Cheng, Chenxi Zhai, Hang Cheng, et al. · arXiv:2609.22688
• Fysiverse-3D-Vision Technical Report: Generating Executable 3D Worlds from Images through Unified Spatial Reasoning Dingkang Yang, Yizhou Liu, Wendong Cheng, et al. · arXiv:2609.25741
• RULER: Instance-aware Rubric Rewards for SVG Generation Hangyu Ran, Yuhao Zheng, Yingying Zhang, et al. · arXiv:2609.25270
• Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents Howard Wang, Han Zheng, Cathy Wu · arXiv:2609.23269