One Model to Train them All: Hierarchical Self-Distillation for Enhanced Early Layer Embeddings Paper • 2503.03008 • Published 11 days ago
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content Paper • 2406.11811 • Published Jun 17, 2024 • 16
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference Paper • 2404.15420 • Published Apr 23, 2024 • 10