Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models Paper • 2601.20354 • Published Jan 28 • 112
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation Paper • 2601.20614 • Published Jan 28 • 120
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization Paper • 2601.05432 • Published Jan 8 • 170
Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning Paper • 2512.24146 • Published Dec 30, 2025 • 14
S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models Paper • 2508.12880 • Published Aug 18, 2025 • 48
