Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
5
0
7
7
Native desktop agents can finally bridge the gap between visual GUI interaction and programmatic code execution by learning a unified action space, achieving state-of-the-art performance on complex real-world tasks.
Open multimodal code intelligence models now rival proprietary systems, driven by a novel rubric-based data synthesis pipeline that precisely evaluates program correctness, code quality, and visual output.
Even the best vision-language models struggle with reliable evaluation of computer-using agents, but OS-Shepherd models offer a low-cost solution that matches their performance.
Visual artifacts are not just supplementary; they are essential for ensuring code correctness in multimodal programming tasks.
OpenMobile proves that high-performing mobile agents can be trained on entirely synthetic, open-source data, closing the gap with closed-source models and enabling broader research.