X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Paper X-AuT: Pruning Audio Encoders in Speech LLMs with Behavioral Probes and Cross-Scale DistillationTL;DRX-AuT is a framework that …
3 min
Efficient Inference
Large Language Models
Transformer
Machine Learning
Knowledge Distillation
Model Compression