LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression Paper • 2403.12968 • Published Mar 19, 2024 • 25
Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings Paper • 2403.07750 • Published Mar 12, 2024 • 22
