3 papers
cs.LG2026
Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback
Seyed Amir Hosseini, Maryam Abdolali, Amirhosein Tavakkoli +4
Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world p…
cs.PL2025
LEGO: A Layout Expression Language for Code Generation of Hierarchical Mapping
Amir Mohammad Tavakkoli, Cosmin Oancea, Mary Hall
We describe LEGO, a new approach to optimizing data movement whereby code is expressed as a layout-independent computation and composed with layouts for data and computation. This…
cs.PL2024
Scheduling Languages: A Past, Present, and Future Taxonomy
Mary Hall, Cosmin Oancea, Anne C. Elster +4
Scheduling languages express to a compiler a sequence of optimizations to apply. Compilers that support a scheduling language interface allow exploration of compiler optimizations,…