Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper • 2602.10604 • Published 3 days ago • 171
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published Jan 8 • 225
BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain Paper • 2512.08560 • Published Dec 9, 2025 • 38
StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation Paper • 2512.09363 • Published Dec 10, 2025 • 72