Qunshan Gu

13 papers A* 1A 1B 1Journal 9Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Adaptive Learned Image Compression with Graph Neural Networks.
CoRR
Yunuo Chen, Bing He, Zezheng Lyu, Hongwei Hu, Qunshan Gu, Yuan Tian, Guo Lu
2026 J jnl
OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data.
CoRR
Yan Zhao, Zhengxue Cheng, Junxuan Zhang, Dajiang Zhou, Qunshan Gu, Qi Wang, Li Song
2026 J jnl
VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling.
CoRR
Ziyang Cheng, Yuhao Wang, Heyang Liu, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2025 J jnl
CS3-Bench: Evaluating and Enhancing Speech-to-Speech LLMs for Mandarin-English Code-Switching.
CoRR
Heyang Liu, Yuhao Wang, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2025 J jnl
DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor.
CoRR
Yan Zhao, Zhengxue Cheng, Junxuan Zhang, Qunshan Gu, Qi Wang, Li Song
2025 A conf
SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant.
INTERSPEECH
Yixuan Hou, Heyang Liu, Yuhao Wang, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2025 J jnl
SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant.
CoRR
Yixuan Hou, Heyang Liu, Yuhao Wang, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2025 J jnl
VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models.
CoRR
Heyang Liu, Yuhao Wang, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2025 J jnl
VocalNet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction.
CoRR
Yuhao Wang, Ziyang Cheng, Heyang Liu, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2025 J jnl
VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation.
CoRR
Yuhao Wang, Heyang Liu, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2025 A* conf
VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation.
EMNLP
Yuhao Wang, Heyang Liu, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
2014 B conf
Improved HEVC lossless compression using two-stage coding with sub-frame level optimal quantization values.
ICIP
Xun Cai, Qunshan Gu
2013 — conf
Towards a next generation open-source video codec.
Visual Information Processing and Communication
Jim Bankoski, Ronald Bultje, Adrian Grange, Qunshan Gu, Jingning Han, John Koleszar, Debargha Mukherjee, Paul Wilkins, Yaowu Xu