activity
20242026
collaborators

27 papers

cs.SD2026

EchoEdit: Stabilizing Inversion-Free Audio Editing via Optimal Transport Geometry

Zhongyuan Fu, Yuhang Jia, Hui Wang +6

Text-guided audio editing with pretrained generative models is commonly implemented through inversion or noising. This topology induces a structural trade-off, as stronger edits re…

cs.SD2026

FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision

Shiyao Wang, Xijuan Zeng, Hui Wang +4

We present FoleyGenEx, a unified video-to-audio (VTA) framework integrating multi-modal control, frame-level temporal alignment, and fine-grained semantics, enabling synchronized,…

eess.AS2026

UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning

Hui Wang, Yifan Yang, Zeyue Tian +8

Audio generation and audio-to-text understanding remain largely separate, with diffusion models dominating high-fidelity synthesis and autoregressive (AR) language models driving c…

cs.CL2026

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning

Shiwan Zhao, Zhihu Wang, Xuyang Zhao +10

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT…

cs.SD2026

Speech-XL: Towards Long-Form Speech Understanding in Large Speech Language Models

Haoqin Sun, Chenyang Lyu, Shiwan Zhao +5

Despite the growing success of Large Speech Language Models (LSLMs) in processing short-term acoustic signals, their extension to long-form audio understanding is severely bottlene…

cs.SD2026

DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding

Jiaming Zhou, Xuxin Cheng, Shiwan Zhao +5

Autoregressive (AR) large audio language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains cost…