collaborators

7 papers

eess.AS2025

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation

Yakun Song, Xiaobin Zhuang, Jiawei Chen +8

Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under d…

cs.CV2025

Heptapod: Language Modeling on Visual Signals

Yongxin Zhu, Jiawei Chen, Yuanzhe Chen +6

We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \textbf{causal attention}, \textbf{eliminate…

eess.AS2025

Direct Preference Optimization for Speech Autoregressive Diffusion Models

Zhijun Liu, Dongya Jia, Xiaoqiang Wang +4

Autoregressive diffusion models (ARDMs) have recently been applied to speech generation, achieving state-of-the-art (SOTA) performance in zero-shot text-to-speech. By autoregressiv…

cs.CV2025

Sounding that Object: Interactive Object-Aware Image to Audio Generation

Tingle Li, Baihe Huang, Xiaobin Zhuang +6

Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an {\em inter…

cs.SD2025

MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation

Yakun Song, Jiawei Chen, Xiaobin Zhuang +9

Neural audio codecs have made significant strides in efficiently mapping raw audio waveforms into discrete token representations, which are foundational for contemporary audio gene…

eess.AS2025

AudioMorphix: Training-free audio editing with diffusion probabilistic models

Jinhua Liang, Yuanzhe Chen, Yi Yuan +5

Editing sound with precision is a crucial yet underexplored challenge in audio content creation. While existing works can manipulate sounds by text instructions or audio exemplar p…