DivMerge: A divergence-based model merging method for multi-tasking Paper • 2509.02108 • Published Sep 2, 2025 • 26
Less is More: Recursive Reasoning with Tiny Networks Paper • 2510.04871 • Published Oct 6, 2025 • 519
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning Paper • 2506.04207 • Published Jun 4, 2025 • 48
