Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 5 days ago • 228
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published 11 days ago • 425
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models Paper • 2604.04780 • Published 7 days ago • 9