7 papers
MoGeFlow: Flowing Through Motion Codebook Geometry for Text-to-Motion Generation
Pengcheng Fang, Tengjiao Sun, Xiaoyu Zhan +2
Vector-quantized motion tokenizers provide a compact discrete interface for text-to-motion generation, but most motion-code priors treat code indices as unordered categorical label…
Privileged Foresight Distillation: Zero-Cost Future Correction for World Action Models
Pengcheng Fang, Hongli Chen, Xiaohao Cai
World action models jointly predict future video and action during training, raising an open question about what role the future-prediction branch actually plays. A recent finding…
HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction
Pengcheng Fang, Hongli Chen, Guangzhen Yao +5
Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence. We present HiFi-MambaV2, a…
When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
Pengcheng Fang, Yuxia Chen, Rui Guo
Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Vid…
GRASPTrack: Geometry-Reasoned Association via Segmentation and Projection for Multi-Object Tracking
Xudong Han, Pengcheng Fang, Yueying Tian +4
Multi-object tracking (MOT) in monocular videos is fundamentally challenged by occlusions and depth ambiguity, issues that conventional tracking-by-detection (TBD) methods struggle…
HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI Reconstruction
Hongli Chen, Pengcheng Fang, Yuxia Chen +6
Reconstructing high-fidelity MR images from undersampled k-space data remains a challenging problem in MRI. While Mamba variants for vision tasks offer promising long-range modelin…