Author

Tianyu Xie

h-index 4 View on Semantic Scholar

We have 3 of 16 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue

Real-time full-duplex speech models can listen while speaking, enabling natural interaction without rigid turn boundaries. Existing benchmarks evaluate turn-taking, interruption handling and multi-round dialogue, but largely centre on a designated user rather than an assistant participating in a shared conversation amo...

Chengqian Ma, Wen-Hao Feng, Wei-Xuan Jin et al. · 0 citations

Jul 2026

WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

WaveZip is proposed, a joint signal-frequency-domain framework for efficient video inference that requires no task-specific training and can be seamlessly integrated into off-the-shelf LVLMs to boost inference efficiency.

Yuhui Zeng, Wang Chen, Jin-Fa Huang et al. · arXiv.org · 1 citation

Preprint Jul 2026

Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation

Modality Subspace Activation (MSA) is proposed, a training-free inference-time framework that uses Singular Value Decomposition (SVD) to estimate modal activation strengths and dynamically balances modal projections in the last hidden state, effectively restoring CMS across benchmarks.

Hongbo Jiang, Jie Li, Yunhang Shen et al. · 0 citations