14 papers
SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation
Qingpo Wuwu, Xiaobao Wei, Peng Chen +6
While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives to capture fine details, lea…
Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
Jingyang He, Guangrun Li, Jieyu Zhang +3
Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with…
World-Ego Modeling for Embodied Video Generation in Long-Horizon Navigation-Manipulation Tasks
Zuyao Lin, Jianhui Zhang, Peidong Jia +4
Embodied video world models typically capture both scene evolution and the robot's behavior, which we refer to as the \emph{world} and the \emph{ego}, respectively. The world and t…
HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
Shuanghao Bai, Meng Li, Xinyuan Lv +15
Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making hi…
Dexora: Open-source VLA for High-DoF Bimanual Dexterity
Zongzheng Zhang, Jingrui Pang, Zhuo Yang +22
Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dextero…
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
Ronyu Zhang, Aosong Cheng, Gaole Dai +8
Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error…
SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding
Pengxin Xu, Xincheng Lin, Luping Xiao +5
General scene perception has progressed from object recognition toward open-vocabulary grounding, part localization, and affordance prediction. Yet these capabilities are often rea…
HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
Qiuxuan Feng, Jiale Yu, Jiaming Liu +8
World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Exec…
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
Hao Wang, Xiaobao Wei, Jingyang He +10
Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image d…
Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models
Yulin Luo, Hao Chen, Zhuangzhe Wu +10
Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately int…
URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets
Zhuangzhe Wu, Yue Xin, Chengkai Hou +4
Articulated objects are fundamental for robotics, simulation of physics, and interactive virtual environments. However, recovering them from visual observations is inherently chall…
URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
Zhe Li, Xiang Bai, Jieyu Zhang +5
Constructing accurate digital twins of articulated objects is essential for robotic simulation training and embodied AI world model building, yet historically requires painstaking…
Orochi: Versatile Biomedical Image Processor
Gaole Dai, Chenghao Zhou, Yu Zhou +6
Deep learning has emerged as a pivotal tool for accelerating research in the life sciences, with the low-level processing of biomedical images (e.g., registration, fusion, restorat…
4D Visual Pre-training for Robot Learning
Chengkai Hou, Yanjie Ze, Yankai Fu +5
General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation task…