تجميع مظاهرات لمسية على الروبوتات مكلفة و بطيئة، مما يحفز استخدام قفازات لمسية بشرية منخفضة التكلفة لجمع بيانات قابلة للتوسع. ومع ذلك، تختلف قفازات الإنسان القادرة على التشغيل والحواسيب اللمسية الروبوتية بشكل أساسي من حيث مبدأ التحويل وتخطيط الحاسوب وقرارة المكان والاستجابة الديناميكية، مما يجعل مصافحة قنوات الحاسوب ال …
Doc2Query, a popular document expansion technique, leverages sequence-to-sequence models to generate relevant queries, effectively addressing the "vocabulary mismatch" problem in information retrieval. However, these models often suffer from generating either hallucinations unrelated to the document or repetitive conte …
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable results. We thus introduce OSWorld-Science, a benchmark and evaluation en …
Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open specifications? Here we introduce ReviveBench, a benchmark with two task families evaluated by hidden verifiers calibrated against native execution environments, establis …
Traffic lights are a key regulatory signal for autonomous driving at urban intersections, yet existing traffic signal perception is still predominantly formulated as instance-level detection or color recognition. Such formulations identify where traffic lights are and what colors they display, but leave a critical sema …