Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models Paper • 2601.20354 • Published 3 days ago • 102
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation Paper • 2601.20614 • Published 3 days ago • 112
BokehDepth: Enhancing Monocular Depth Estimation through Bokeh Generation Paper • 2512.12425 • Published Dec 13, 2025 • 2
Urban Socio-Semantic Segmentation with Vision-Language Reasoning Paper • 2601.10477 • Published 16 days ago • 155
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization Paper • 2601.05432 • Published 23 days ago • 165
Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning Paper • 2512.24146 • Published Dec 30, 2025 • 14
DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 472