collaborators

8 papers

cs.LG2025

Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-Experts

Qi Wang, Hanyang Peng, Yue Yu

Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of trai…

cs.SD2025

Fed-PISA: Federated Voice Cloning via Personalized Identity-Style Adaptation

Qi Wang, Shituo Ma, Guoxin Yu +2

Voice cloning for Text-to-Speech (TTS) aims to generate expressive and personalized speech from text using limited data from a target speaker. Federated Learning (FL) offers a coll…

cs.LG2025

GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning

Han Zhang, Ruibin Zheng, Zexuan Yi +16

As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing l…

cs.LG2025

SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam

Hanyang Peng, Shuang Qin, Yue Yu +3

Adam has proven remarkable successful in training deep neural networks, but the mechanisms underlying its empirical successes and limitations remain underexplored. In this study, w…

cs.LG2025

Simple Convergence Proof of Adam From a Sign-like Descent Perspective

Hanyang Peng, Shuang Qin, Yue Yu +3

Adam is widely recognized as one of the most effective optimizers for training deep neural networks (DNNs). Despite its remarkable empirical success, its theoretical convergence an…

cs.SD2025

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

Haiyun Li, Zhiyong Wu, Xiaofeng Xie +3

Voice cloning (VC)-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by trai…