Author

Zhiyong Wu

Observed name: Wu, Zhiyong

Institutions: Chinese University of Hong Kong, Huawei Technologies (China), University Town of Shenzhen, Tsinghua–Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, University of Hong Kong, Tsinghua University

Observed institutions: Chinese University of Hong Kong, Princeton University, Huawei Technologies (China), University Town of Shenzhen, Tsinghua–Berkeley Shenzhen Institute, Shanghai Artificial Intelligence Laboratory, Tsinghua Shenzhen International Graduate School, East China Normal University, University of Hong Kong, Tsinghua University

OpenAlex ID: A5121832101

OS-Copilot: Towards Generalist Computer Agents with Self-Improvement

2024 · Wu, Zhiyong, Han, Chengcheng, et al. · arXiv (Cornell University) · 6

PDF

UniStream: Multi-Expert Residual Vector Quantization for 48 kHz Causal Streaming Audio Coding

2026 · Zhao, Mingyu, Wu, Zhiyong · arXiv (Cornell University)

PDF

SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generation

2026 · Cai, Yunrui, Li, Xu, et al. · arXiv (Cornell University)

PDF

BAMU: Bitstream-Aware Marginal-Utility Allocation for Frozen Pretrained Neural Speech Codecs

2026 · Zhao, Mingyu, Lin, Zijian, et al. · arXiv (Cornell University)

PDF

EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal

2026 · Wu, Feier, Xia, Wanke, et al. · arXiv (Cornell University)

PDF

Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model

2026 · Lin, Zhiwei, Chen, Jun, et al. · arXiv (Cornell University)

PDF

TurnFSM for Full-Duplex Dialogue System: Internalizing State-Machine Logic for Streaming Semantic Voice Activity Detection and Utterance-Level Rejection

2026 · Lin, Zhiwei, Du, Tianjiao, et al. · arXiv (Cornell University)

PDF

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

2026 · Sun, Qiushi, Cheng, Kanzhi, et al. · arXiv (Cornell University)

PDF

Qwen-Music Technical Report

2026 · Xu, Jin, Wang, Kangdi, et al. · arXiv (Cornell University)

PDF

Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimization

2026 · Peng, Shuhai, Liu, Jinjiang, et al. · arXiv (Cornell University)

PDF

Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies

2026 · Shen, Xudong, Yuan, Li, et al. · arXiv (Cornell University)

PDF

LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training

2026 · Lei, Shun, Zhang, Huaicheng, et al. · arXiv (Cornell University)

PDF

FineCombo-TTS: Collaborative and Precise Controllable Speech Synthesis Using Text Descriptions and Reference Speech

2026 · Zhou, Shuoyi, Zhou, Yixuan, et al. · arXiv (Cornell University)

PDF

Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment

2026 · Li, Xiang, Zhou, Yixuan, et al. · arXiv (Cornell University)

PDF

Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions

2026 · Li, Haiyun, Peng, Shuhai, et al. · arXiv (Cornell University)

PDF

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

2026 · Zhu, Liya, Ding, Jingzhe, et al. · arXiv (Cornell University)

PDF

Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization

2026 · Xu, Ziang, Yu, Wenbo, et al. · arXiv (Cornell University)

PDF

VoxCPM2 Technical Report

2026 · Zhou, Yixuan, Zeng, Guoyang, et al. · arXiv (Cornell University)

PDF

How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue

2026 · Lu, Hui, Chen, Xueyuan, et al. · arXiv (Cornell University)

PDF

TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis

2026 · Wang, Xi, Wang, Jie, et al. · arXiv (Cornell University)

PDF

StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

2026 · Peng, Shuhai, Lu, Hui, et al. · arXiv (Cornell University)

PDF

The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models

2026 · Dinkel, Heinrich, Zhou, Jiahao, et al. · arXiv (Cornell University)

PDF

LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation

2026 · Zhisheng Zhang, Xiang Li, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping

2025 · He, Xu, Zhang, Haoxian, et al. · arXiv (Cornell University)

PDF

Works count: 24

Citation count: 6

H-index: 1

I10-index: