2 papers
cs.AI2026
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
Dingyuan Dai, Heli Qi, Lei Liu +28
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized int…
cs.RO2026
CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts
Tianhang Pan, Xuanhao Wang, Yiwen Pang +4
VLAs combine pretrained vision-language representations with action generation to enable language-guided control across diverse tasks, becoming a mainstream paradigm in embodied in…