Submitted by QiushiSun 82 OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis · 15 authors 3
Submitted by topyun 20 Are Vision-Language Models Truly Understanding Multi-vision Sensor? · 6 authors 2
Submitted by freesunshine0316 11 HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving · 7 authors 2
Submitted by fenfan 10 VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control · 5 authors 2