Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering Paper • 2505.02311 • Published May 5 • 2
SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models Paper • 2503.07605 • Published Mar 10 • 69
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System Paper • 2503.09600 • Published Mar 12 • 4
Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception Paper • 2410.12788 • Published Oct 16, 2024 • 24