IterPref: Focal Preference Learning for Code Generation via Iterative Debugging Paper • 2503.02783 • Published Mar 4 • 6
Gradient-Mask Tuning Elevates the Upper Limits of LLM Performance Paper • 2406.15330 • Published Jun 21, 2024
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training Paper • 2411.14318 • Published Nov 21, 2024
EpiCoder: Encompassing Diversity and Complexity in Code Generation Paper • 2501.04694 • Published Jan 8 • 16