Qunshan Gu

4 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13) 📈 Trend Setter

Venues

CVPR (2) EMNLP (1) Interspeech (1)

Top co-authors

Yu Wang (2) Yanfeng Wang (2) Heyang Liu (2) Yuhao Wang (2) Ziyang Cheng (2) Ronghua Wu (2) Li Song (1) Guo Lu (1) Yixuan Hou (1) Bing He (1)

Research topics

Artificial Intelligence (4) Core AI (4) Deep Learning (2) Natural Language Processing (2) Speech & Audio (2) Computer Vision (1) Machine Learning (1) Applications (1) Architectures (1) Learning Types (1) Optimization & Theory (1) Processing (1) Recognition (1) Resources & Methods (1) Synthesis (1)

Keywords

speech generation (2) large language model (2) speech recognition (1) speech processing (1) context modeling (1) receptive field (1) lossless compression (1) next-token prediction (1) inference speed (1) edge device inference (1) multi-token prediction (1) speech quality (1) voice assistant (1) two-stage training (1) learned image compression (1) graph neural network (1) speech llm (1) multi-modal tokenizer (1) acoustic quality (1) content-adaptive compression (1)

Papers

Adaptive Learned Image Compression with Graph Neural Networks CVPR 2026 OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data CVPR 2026 SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant Interspeech 2025 VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation EMNLP 2025