Metric-Bench introduces a new benchmark for Vision‑Language Models (VLMs) that focuses on metric‑spatial reasoning in indoor scenes by using in‑image reference objects with known dimensions. The accompanying MetricReasoner fine‑tuning recipe employs structured prompts and numerical rewards to implicitly learn 2D‑to‑3D mapping without camera intrinsics. Experiments show that this approach improves spatial metric understanding by 43.1 % over existing models and boosts downstream embodied tasks, while also delivering gains on general VLM benchmarks.
By Yuling Xi, Haokai Zhang, Muzhi Zhu, Hao Zhong, Zongze Du, Hengyu Zhao, Chenchen Jing, Yufei Yin, Bin Qin, Yongjie Yang, Zhenbo Luo, Hao Chen, Chunhua Shen
arXiv:2602. 19710v3 Announce Type: replace-cross Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision.
By Haitao Lin, Hanyang Yu, Jingshun Huang, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu
arXiv:2609.06880v1 Announce Type: cross
Abstract: Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated pers...
By Mimo Shirasaka, Haochen Zhang, Yonatan Bisk
arXiv:2609.33462v2 Announce Type: replace
Abstract: Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use...
By Shriram Damodaran, Soumyaratna Debnath, Cheston Tan, Lin Wang
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo
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:2606. 30632v1 Announce Type: cross Abstract: Can the robot use a plate to cut a cake if no knife is available?
By Yuhong Deng, Yuyao Liu, David Hsu
The paper introduces 3DWay, a method that predicts 3D consistent waypoints for robot manipulation using multi‑view images. By first generating 2D waypoints that are consistent across views and then triangulating them, the approach provides explicit 3D motion specifications while leveraging pretrained vision‑language models. Experiments demonstrate that 3DWay improves 3D spatial grounding and vision‑language reasoning, enhancing the generalization of robot manipulation policies.
The paper introduces 3DWay, a method that predicts 3D-consistent waypoints for robot manipulation by first generating multi‑view consistent 2D waypoints and then triangulating them. This approach addresses the 3D ambiguity inherent in 2D trajectory predictions and leverages pretrained vision‑language models to provide explicit 3D motion specifications. Experiments demonstrate that 3DWay improves 3D spatial grounding and vision‑language reasoning, enhancing generalization for robot manipulation tasks.
By Ziqin Huang, Yingyue Li, Chenyangguang Zhang, Ruida Zhang, Yuxin Chen, Gu Wang, Xingyu Liu, Masayoshi Tomizuka, Xiangyang Ji
arXiv:2606. 06761v1 Announce Type: cross Abstract: Visuomotor manipulation policies trained via large-scale behavior cloning have achieved strong semantic scene understanding, yet often fail to reliably execute correct low-level actions under distribution shifts.
By Jiyun Jang, Yujin Sung, Woosung Joung, Daewon Chae, Sangwon Lee, Sohwi Kim, Jinkyu Kim, Jungbeom Lee
MV-STRIDE is a Multi‑View hierarchical Spatial Reasoning dataset that models dependencies among perception, scene understanding, and contextual reasoning to support 3D spatial cognition. It introduces a QA generation pipeline that enforces cross‑view constraints, producing multi‑level reasoning tasks with chain‑of‑thought supervision. Experiments show that training on MV‑STRIDE yields state‑of‑the‑art performance on multi‑view spatial benchmarks, enabling MLLMs to reason robustly across diverse viewpoints.
By Jin Xu, Xiaojian Huang, Zhuodong Luo, Zhihong Zhang, Xin Liu, Jiansheng Wei, Xinzhi Wang, Jie Zhao, Xuejin Chen
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.
By Haibo Wang, Lifu Huang