MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design Paper • 2412.14590 • Published 8 days ago • 12
BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion Paper • 2408.04785 • Published Aug 8 • 7
MulliVC: Multi-lingual Voice Conversion With Cycle Consistency Paper • 2408.04708 • Published Aug 8 • 6