activity
20242026
collaborators

7 papers

cs.SD2026

Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech

Xuanjun Chen, Yun-Shing Wu, Wei-Chung Lu +4

Recent neural audio codec-based speech generation (CodecFake) produces highly realistic audio, posing a challenge to existing deepfake countermeasure models. While using codec resy…

cs.CL2026

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs

Longxuan Yu, Yunshu Wu, Yu Fu +5

Discrete Masked diffusion language models generate text by iterative parallel decoding, but few-step decoding suffers from a tradeoff between length and quality: with a fixed step…

cs.LG2026

Discrete Stochastic Localization for Non-autoregressive Generation

Yunshu Wu, Jiayi Cheng, Longxuan Yu +4

Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generatio…

cs.LG2026

Discrete Stochastic Localization for Non-autoregressive Generation

Yunshu Wu, Jiayi Cheng, Longxuan Yu +4

Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generatio…

cs.LG2026

Spectral Regularization for Diffusion Models

Satish Chandran, Nicolas Roque dos Santos, Yunshu Wu +2

Diffusion models are typically trained using pointwise reconstruction objectives that are agnostic to the spectral and multi-scale structure of natural signals. We propose a loss-l…

cs.LG2025

Measurement-Aligned Sampling for Inverse Problem

Shaorong Zhang, Rob Brekelmans, Yunshu Wu +1

Diffusion models provide a powerful way to incorporate complex prior information for solving inverse problems. However, existing methods struggle to correctly incorporate guidance…