Research

Below are my papers on the foundations and reliability of large AI models. They are also listed on Google Scholar and arXiv.

Papers

• SMat-Attention: Structured Long-Context Sequence Modeling Emile Anand, Abdullah Ateyeh, Archer Wang, Marin Soljačić Under review at ICLR 2027. Long Context Frontier Models Workshop, NeurIPS 2026. arXiv PDF Code
• Continuous Latent Contexts Enable Efficient Online Learning in Transformers Emile Anand, Abdullah Ateyeh, Xinyuan Cao, Max Dabagia Under review at ICLR 2027. arXiv PDF