collaborators

8 papers

q-bio.GN2026

Making Single-Cell Data Distillation Auditable: Traceable Real-Cell Coresets via Discrete Min--Max Selection

Yaodi Luo, Peize He, Lingbei Meng +5

Large single-cell datasets are expensive to store, curate, and repeatedly reuse for model training. Data distillation can reduce this burden by building smaller training sets. Howe…

cs.SD2026

Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models

Yuxuan Chen, Haoyuan Yu, Peize He

Recent spatial self supervised audio models achieve high performance on localization tasks, raising questions about their encoding of microsecond interaural phase fine structures.…

cs.SD2026

Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models

Yuxuan Chen, Haoyuan Yu, Peize He

Flow-matching transformers achieve strong audio separation, yet their attention dynamics are opaque. We adapt established causal-intervention principles into a deterministic, infer…

cs.CV2026

VidNum: Diagnosing VLM Failure Modes in Video-Grounded Numerical Reasoning

Shaoyang Cui, Lingbei Meng, Yaodi Luo +1

Video-grounded numerical reasoning requires Vision-Language Models (VLMs) to identify, track, and combine quantitative evidence across frames, actions, and scene changes. Existing…

cs.SD2026

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models

Peize He, Yaodi Luo, Xiaoqian Liu +7

Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference costs. Token compression is an…

cs.SD2026

AudioKV: KV Cache Eviction in Efficient Large Audio Language Models

Yuxuan Wang, Peize He, Xiyan Gui +6

Large Audio-Language Models (LALMs) have set new benchmarks in speech processing, yet their deployment is hindered by the memory footprint of the Key-Value (KV) cache during long-c…