MixSD: Mixed Contextual Self-Distillation for Knowledge Injection Paper • 2605.16865 • Published 6 days ago • 5
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection Paper • 2605.16865 • Published 6 days ago • 5
Dual-View Training for Instruction-Following Information Retrieval Paper • 2604.18845 • Published Apr 20 • 10
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers Paper • 2604.17632 • Published Apr 19 • 11
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision Paper • 2604.12002 • Published Apr 13 • 12