World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning Paper • 2503.10480 • Published 2 days ago • 37
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation Paper • 2502.14846 • Published 23 days ago • 13
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? Paper • 2502.12215 • Published 27 days ago • 16