3 papers
cs.LG2026
Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights
Naoya Chiba, Satoshi Sugiyama, Yuki Uranishi
Post-hoc analysis of trained neural network weights often seeks to recover geometric structure directly from the parameters. We show that, for positional-encoding-equipped neural f…
cs.CV2026
3DGesPolicy: Phoneme-Aware Holistic Co-Speech Gesture Generation Based on Action Control
Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita +2
Generating holistic co-speech gestures that integrate full-body motion with facial expressions suffers from semantically incoherent coordination on body motion and spatially unstab…
cs.CV2025
3DFacePolicy: Audio-Driven 3D Facial Animation Based on Action Control
Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita +2
Audio-driven 3D facial animation has achieved significant progress in both research and applications. While recent baselines struggle to generate natural and continuous facial move…