Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers Paper • 2504.20752 • Published Apr 29, 2025 • 93
VSC-RL: Advancing Autonomous Vision-Language Agents with Variational Subgoal-Conditioned Reinforcement Learning Paper • 2502.07949 • Published Feb 11, 2025 • 1