@article{towardsguiagentsvisionlanguagediffusionm, title = {Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding}, author = {Shrinidhi Kumbhar and Haofu Liao and Srikar Appalaraju and Kunwar Yashraj Singh}, year = {2026}, eprint = {2603.26211}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.26211}, }