4 papers
StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
Jiasong Xiao, Yutao She, Kai Li +2
Vision-language-action (VLA) models integrate visual observations and language instructions to predict robot actions, demonstrating promising generalization in manipulation tasks.…
Open-World Video Segmentation
Qing Su, Kaiyang Li, Yuan Zhuang +2
While video segmentation has advanced rapidly on short clips and closed-set benchmarks, open-world video segmentation remains largely unexplored. The challenge is twofold: (1) exis…
ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control
Haosen Wang, Zhenyang Li, Yinqiang Zhang +9
Zero-shot object navigation has advanced rapidly with open-vocabulary detectors, image--text models, and language-guided exploration. However, even after current methods detect a p…
Bayesian Model Merging
Kaiyang Li, Shaobo Han, Qing Su +1
Model merging aims to combine multiple task-specific expert models into a single model without joint retraining, offering a practical alternative to multi-task learning when data a…