QG
Qunshan Gu
cs.CLcs.AIcs.CVcs.SDeess.AScs.IRcs.ITcs.LGcs.MMmath.IT
On Valency
published · living versionsW_wrsmdxgm·v1 · currentpublished
Speech LLMs That Breathe: Modeling Non-Verbal Vocalizations in Dialogue
with Heyang Liu, Lixin Zhang, Jiayi Huang, Ziyang Cheng +4
1 version
Preprints & journals
17 papers in the corpus · 2024–2026Speech LLMs That Breathe: Modeling Non-Verbal Vocalizations in Dialogue2610.25942v1 · Heyang Liu, Lixin Zhang, Jiayi Huang et al.2026 · 0 citationsarXivon Valency
-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants2609.09852v1 · Heyang Liu, Jiayi Huang, Wenyang Xiao et al.2026 · 0 citationsarXiv
Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding2608.08832v1 · Donghui Feng, Fengxi Zhang, Changsheng Gao et al.2026 · 0 citationsarXiv
LaSR: Context-Aware Speech Recognition via Latent Reasoning2606.00507v2 · Heyang Liu, Ziyang Cheng, Jiayi Huang et al.2026 · 0 citationsarXiv
Adaptive Learned Image Compression with Graph Neural Networks2603.25316v1 · Yunuo Chen, Bing He, Zezheng Lyu et al.2026 · 0 citationsarXiv
OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data2602.22286v2 · Yan Zhao, Zhengxue Cheng, Junxuan Zhang et al.2026 · 0 citationsarXiv
VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling2602.08607v1 · Ziyang Cheng, Yuhao Wang, Heyang Liu et al.2026 · 0 citationsarXiv
WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search2604.06177v1 · Yuelin Hu, Zhengxue Cheng, Ronghua Wu et al.2026 · 0 citationsarXiv
VocalNet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction2511.10232v1 · Yuhao Wang, Ziyang Cheng, Heyang Liu et al.2025 · 0 citationsarXiv
VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context2511.08230v2 · Heyang Liu, Ziyang Cheng, Yuhao Wang et al.2025 · 0 citationsarXiv
CS3-Bench: Evaluating and Enhancing Speech-to-Speech LLMs for Mandarin-English Code-Switching2510.07881v1 · Heyang Liu, Yuhao Wang, Ziyang Cheng et al.2025 · 0 citationsarXiv
SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant2506.02457v1 · Yixuan Hou, Heyang Liu, Yuhao Wang et al.2025 · 2 citationsarXiv
DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor2505.16256v1 · Yan Zhao, Zhengxue Cheng, Junxuan Zhang et al.2025 · 0 citationsarXiv
VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models2505.15727v3 · Heyang Liu, Yuhao Wang, Ziyang Cheng et al.2025 · 1 citationarXiv
VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation2504.04060v2 · Yuhao Wang, Heyang Liu, Ziyang Cheng et al.2025 · 1 citationarXiv
Instance-Adaptive Spatial-Temporal Enhancement for Efficient Video Compression.40889314 · Zhao, Yan, Cheng, Zhengxue, Li, Jiangchuan et al.2025 · 4 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025;34:5776-5791
H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting2408.13036v3 · Bing He, Yunuo Chen, Guo Lu et al.2024 · 2 citationsarXiv
Career total: 23 works. 17 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.