Machine Learning Papers

Week of May 17 – May 24, 2026

← Previous Week | Current Week →

🏆 Top Papers This Week

#1 TOP PAPER (Score: 90)
Ruitao Liu, Xinyang Tian, Shuo Chen ... · arXiv
Pipeline parallelism is a key technique for scaling large-model training, but modern workloads exhibit runtime variability in computation and communication. Existing pipeline systems typically consume static, profiled, or adaptively generated schedules as pre-committed execution ...
#2 TOP PAPER (Score: 89)
Dayal Singh Kalra, Maissam Barkeshli · arXiv
Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large language models (LLMs). This is done either by fitting a scaling law to the hyperparameters or by a judicious choice of parameteriza...
#3 TOP PAPER (Score: 84)
Mohammed Alshaalan, Miguel R. D. Rodrigues · ICML 2026
Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point detection problem over the token-level next-...