Qunshan Gu

Computer Science · Physical Sciences

2h-index53citations16works0.12yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(5), Natural Language Processing Techniques(4), Video Coding and Compression Technologies(3), Advanced Data Compression Techniques(3), Speech and dialogue systems(3)

Publications16 total

OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
arXiv (Cornell University)·2026Open Access
OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
arXiv (Cornell University)·2026Open Access
VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling
arXiv (Cornell University)·2026Open Access
VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling
arXiv (Cornell University)·2026Open Access
VocalNet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction
arXiv (Cornell University)·2025Open Access
VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context
arXiv (Cornell University)·2025Open Access
CS3-Bench: Evaluating and Enhancing Speech-to-Speech LLMs for Mandarin-English Code-Switching
arXiv (Cornell University)·2025Open Access
SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant
2025
SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant
ArXiv.org·2025· 1 citedOpen Access
DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor
arXiv (Cornell University)·2025Open Access
VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models
arXiv (Cornell University)·2025Open Access
VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation
arXiv (Cornell University)·2025· 1 citedOpen Access
Instance-Adaptive Spatial-Temporal Enhancement for Efficient Video Compression
IEEE Transactions on Image Processing·2025
VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation
2025Open Access
Improved HEVC lossless compression using two-stage coding with sub-frame level optimal quantization values
2014· 8 cited
Towards a next generation open-source video codec
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE·2013· 43 cited

Frequent Co-authors

Heyang Liu(10), Ziyang Cheng(8), Ronghua Wu(8), Yanfeng Wang(8), Yu Wang(8), Yuhao Wang(7), Junxuan Zhang(3), Yunfei Hou(2), Ziyang Cheng(2), Yuhao Wang(2), Ronghua Wu(2), Yanfeng Wang(2), Yu Wang(2), Yan Zhao(2), Zhengxue Cheng(2), Dajiang Zhou(2), Qi Wang(2), Li Song(2), Jim Bankoski(1), Ronald S. Bultje(1)