NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale Paper • 2508.10711 • Published 11 days ago • 136
view article Article ✴️ ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use By Ziyang and 1 other • Jan 3 • 19
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models Paper • 2501.02955 • Published Jan 6 • 45