@article{mixatlasuncertaintyawaredatamixtureoptim, title = {MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining}, author = {Bingbing Wen and Sirajul Salekin and Feiyang Kang and Bill Howe and Lucy Lu Wang and Javier Movellan and Manjot Bilkhu}, year = {2026}, eprint = {2604.14198}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.14198}, }