6 papers · 1 filter
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…
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…
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…
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…
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…