11 papers
SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models
Md Kawsher Mahbub, Milon Biswas, Mirza Niaz Morshed +1
Clinical vision models are often deployed as frozen black boxes with no access to internals, retraining, or ground truth at inference time. We introduce \textbf{SpatialUQ}, a post-…
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
Taowen Wang, Zikang Xie, Bin Yang +13
Humanoid robots promise whole-body interaction in human-centered environments, but scalable policy learning remains difficult because task-level decision-making and whole-body dyna…
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Jiawen Wen, Penglei Sun, Wenjie Zhang +4
As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachability to social compliance. Howev…
Morphology-Consistent Humanoid Interaction through Robot-Centric Video Synthesis
Weisheng Xu, Jian Li, Yi Gu +12
Equipping humanoid robots with versatile interaction skills typically requires either extensive policy training or explicit human-to-robot motion retargeting. However, learning-bas…
Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control
Weisheng Xu, Qiwei Wu, Jiaxi Zhang +7
Physics-based humanoid control relies on training with motion datasets that have diverse data distributions. However, the fixed difficulty distribution of datasets limits the perfo…
Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?
Boyang Cai, Qiwei Liang, Jiawei Li +11
Does multi-view demonstration truly improve robot manipulation, or merely enhance cross-view robustness? We present a systematic study quantifying the performance gains, scaling be…
UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing
Jiaxi Zhang, Yunheng Wang, Wei Lu +8
3D Visual Grounding (3DVG) localizes objects from natural-language descriptions in 3D scenes and is fundamental to embodied AI applications. Although foundation models enable open-…
Spherical Latent Motion Prior for Physics-Based Simulated Humanoid Control
Jing Tan, Weisheng Xu, Xiangrui Jiang +11
Learning motion priors for physics-based humanoid control is an active research topic. Existing approaches mainly include variational autoencoders (VAE) and adversarial motion prio…
T2MBench: A Benchmark for Out-of-Distribution Text-to-Motion Generation
Bin Yang, Rong Ou, Weisheng Xu +7
Most existing evaluations of text-to-motion generation focus on in-distribution textual inputs and a limited set of evaluation criteria, which restricts their ability to systematic…
FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
Tan Jing, Shiting Chen, Yangfan Li +2
Unified physics-based humanoid controllers are pivotal for robotics and character animation, yet models that excel on gentle, everyday motions still stumble on explosive actions, h…
PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds
Weisheng Xu, Sifan Zhou, Jiaqi Xiong +2
LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving. Existing 3D SOT methods typically adhere to a point-based processing pipeline…