arxiv:2608.13560
YaxinLuo PRO
YaxinLuo
AI & ML interests
AudioVisual Speaker extraction, video understanding, self-supervised large speech models
Recent Activity
updated a dataset 3 days ago
figmirror/figmirror-transfer-data authored a paper 4 days ago
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design authored a paper 4 days ago
LLMSurgeon: Diagnosing Data Mixture of Large Language ModelsOrganizations
