@article{directvisualgroundingbydirectingattentio, title = {Direct Visual Grounding by Directing Attention of Visual Tokens}, author = {Parsa Esmaeilkhani and Longin Jan Latecki}, year = {2025}, eprint = {2511.12738}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2511.12738}, }