@article{swangptanefficientandscalableapproach, title = {SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling}, author = {Krishna C. Puvvada and Faisal Ladhak and Santiago Akle Serrano and Cheng-Ping Hsieh and Shantanu Acharya and Somshubra Majumdar and Fei Jia and Samuel Kriman and Simeng Sun and Dima Rekesh and Boris Ginsburg}, year = {2025}, eprint = {2504.08719}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.08719v1}, }