9 papers
Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector
Wenqiang Zu, Shenghao Xie, Bo Lei +1
Recent progress in generative modeling has enabled high-quality visual synthesis with diffusion-based frameworks, supporting controllable sampling and large-scale training. Inferen…
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…
Seeing the Unseen in Low-light Spike Streams
Liwen Hu, Yang Li, Mianzhi Liu +5
Spike camera, a type of neuromorphic sensor with high-temporal resolution, shows great promise for high-speed visual tasks. Unlike traditional cameras, spike camera continuously ac…
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…