8 papers
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
Bowen Li, Shaotong Guo, Zhen Wang +11
Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers…
IR: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
Mohammad Beigi, Ming Jin, Junshan Zhang +3
Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without ge…
Parallel Complex Diffusion for Scalable Time Series Generation
Rongyao Cai, Yuxi Wan, Kexin Zhang +4
Diffusion models learn data distributions indirectly through denoising, making the difficulty of generative modeling closely tied to the dependency structure of data. For time seri…
Spoofing-Aware Speaker Verification via Wavelet Prompt Tuning and Multi-Model Ensembles
Aref Farhadipour, Ming Jin, Valeriia Vyshnevetska +3
This paper describes the UZH-CL system submitted to the SASV section of the WildSpoof 2026 challenge. The challenge focuses on the integrated defense against generative spoofing at…
ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution
Hui Sun, Chang Xu, Haonan Xie +7
LLM-driven Anomaly Detection (AD) helps enhance the understanding and explanatory abilities of anomalous behaviors in Time Series (TS). Existing methods face challenges of inadequa…
OATS: Online Data Augmentation for Time Series Foundation Models
Junwei Deng, Chang Xu, Jiaqi W. Ma +5
Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to improve the training data quality. E…
Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations
Yichen Han, Xiaoyang Hao, Keming Chen +25
Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, whi…
Preparing for Black Swans: The Antifragility Imperative for Machine Learning
Ming Jin
Operating safely and reliably despite continual distribution shifts is vital for high-stakes machine learning applications. This paper builds upon the transformative concept of ``a…