@article{irefvlaabenchmarkforinteractive, title = {IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes}, author = {Haochen Zhang and Nader Zantout and Pujith Kachana and Ji Zhang and Wenshan Wang}, year = {2025}, eprint = {2503.17406}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.17406v1}, }