8 papers
PFM-HR: Pose Flow Matching for Humanoid Robots
Yukang Gao, Yi Gu, Yangchen Zhou +9
Motion priors improve reinforcement learning for physics-based humanoid tracking, but temporal priors require ordered motion clips, while pose priors provide limited guidance for p…
HandFlow: Fully Generative 4D Hand Recovery with Flow Matching
Mingxi Xu, Bowen Duan, Yi Gu +3
Accurate monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions. Temporal models impr…
VEPHand: View-Efficient Photometric Hand Performance Capture at Scale
Zhengyang Shen, Kai-Hung Chang, Erroll Wood +18
Robust, high-fidelity 3D hand capture, while fundamental to digital human creation, remains challenging with practical multi-view systems that balance rich photometry with the geom…
High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians
Bo Peng, Xu Chen, Yi Gu +6
The growing demand for high-fidelity 4D hand-object interaction (HOI) data in embodied AI and spatial computing is currently bottlenecked by the reliance on pre-scanned object temp…
Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions
Ayce Idil Aytekin, Xu Chen, Zhengyang Shen +4
We present Grasp in Gaussians (GraG), a fast and robust method for reconstructing dynamic 3D hand-object interactions from a single monocular video. Unlike recent approaches that o…
Structured Contrastive Learning for Interpretable Latent Representations
Zhengyang Shen, Hua Tu, Mayue Shi
Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to…
CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection
Zhengyang Shen, Xuehao Zhai, Hua Tu +1
Chagas disease affects nearly 6 million people worldwide, with Chagas cardiomyopathy representing its most severe complication. In regions where serological testing capacity is lim…
COBRA: Multimodal Sensing Deep Learning Framework for Remote Chronic Obesity Management via Wrist-Worn Activity Monitoring
Zhengyang Shen, Bo Gao, Mayue Shi
Chronic obesity management requires continuous monitoring of energy balance behaviors, yet traditional self-reported methods suffer from significant underreporting and recall bias,…