OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published 26 days ago • 342
Adversarial Decoding: Generating Readable Documents for Adversarial Objectives Paper • 2410.02163 • Published Oct 3, 2024
Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation Paper • 2510.17555 • Published Oct 20, 2025 • 1
Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation Paper • 2510.17555 • Published Oct 20, 2025 • 1