SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments Paper β’ 2604.14144 β’ Published Apr 15 β’ 63
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper β’ 2602.10604 β’ Published Feb 11 β’ 199
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper β’ 2602.10604 β’ Published Feb 11 β’ 199
Unhackable Temporal Rewarding for Scalable Video MLLMs Paper β’ 2502.12081 β’ Published Feb 17, 2025 β’ 1
Perception-R1: Pioneering Perception Policy with Reinforcement Learning Paper β’ 2504.07954 β’ Published Apr 10, 2025