6 papers
CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation
Yushan Liu, Peibo Sun, Xintao Chao +8
Vision-language-action (VLA) policies commonly execute long-horizon mobile manipulation through open-loop action chunks, issuing multiple actions without receiving new high-level v…
FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
Fangda Chen, Shanshan Zhao, Longrong Yang +3
Video diffusion models perform well in short-video synthesis, but their training-free extension to long videos often suffers from content drift, temporal inconsistency, and over-sm…
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
Yushan Liu, Peibo Sun, Shoujie Li +7
World Action Models (WAMs) enhance Vision-Language-Action policies by jointly predicting scene evolution and robot actions, but existing methods usually represent the predicted wor…
SWGCN: Synergy Weighted Graph Convolutional Network for Multi-Behavior Recommendation
Fangda Chen, Yueyang Wang, Chaoli Lou +2
Multi-behavior recommendation paradigms have emerged to capture diverse user activities, forecasting primary conversions (e.g., purchases) by leveraging secondary signals like brow…
JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation
Fangda Chen, Shanshan Zhao, Chuanfu Xu +1
Recent advancements in customized video generation have led to significant improvements in the simultaneous adaptation of appearance and motion. Typically, decoupling the appearanc…
Few-shot Calligraphy Style Learning
Fangda Chen, Jiacheng Nie, Lichuan Jiang +1
We introduced "Presidifussion," a novel approach to learning and replicating the unique style of calligraphy of President Xu, using a pretrained diffusion model adapted through a t…