6 papers
Motus: A Unified Latent Action World Model
Hongzhe Bi, Hengkai Tan, Shenghao Xie +13
While a general embodied agent must function as a unified system, current methods are built on isolated models for understanding, world modeling, and control. This fragmentation pr…
Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding
Zhiyuan Jiang, Shenghao Xie, Wenyi Li +8
Grounding is a fundamental capability for building graphical user interface (GUI) agents. Although existing approaches rely on large-scale bounding box supervision, they still face…
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks
Junliang Ye, Shenghao Xie, Ruowen Zhao +5
3D object editing is essential for interactive content creation in gaming, animation, and robotics, yet current approaches remain inefficient, inconsistent, and often fail to prese…
Exploring Representation Invariance in Finetuning
Wenqiang Zu, Shenghao Xie, Hao Chen +9
Foundation models pretrained on large-scale natural images are widely adapted to various cross-domain low-resource downstream tasks, benefiting from generalizable and transferable…
Pre-trained Models Succeed in Medical Imaging with Representation Similarity Degradation
Wenqiang Zu, Shenghao Xie, Hao Chen +1
This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained mo…
Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective
Shenghao Xie, Wenqiang Zu, Mingyang Zhao +6
Autoregression in large language models (LLMs) has shown impressive scalability by unifying all language tasks into the next token prediction paradigm. Recently, there is a growing…