Xinyu Yang

6

Papers

22

Total Citations

Papers (6)

Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction

Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity

Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales

Tracking and Understanding Object Transformations

NeurIPS 2025arXiv

MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotion

Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference