Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning Paper • 2504.08672 • Published Apr 11 • 55
Breaking the Data Barrier -- Building GUI Agents Through Task Generalization Paper • 2504.10127 • Published Apr 14 • 17
$φ$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation Paper • 2503.13288 • Published Mar 17 • 51