-
Attention Follows the Work: Foveated Transformer Worktrees for Coding Agents
Peter Zatloukal. Preprint, 2026. Working-backwards draft of November 2, 2026 (revision 3): numbers marked with a dagger are pre-registered targets, not measurements; the rest are measured or quoted from the literature.
-
OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari. ICML Workshop on Efficient Systems for Foundation Models, 2024.
-
eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models
Minsik Cho, Keivan A. Vahid, Qichen Fu, Saurabh Adya, Carlo C. Del Mundo, Mohammad Rastegari, Devang Naik, Peter Zatloukal. IEEE Computer Architecture Letters 23(1), pp. 37–40, 2024.