Subliminal Learning: Language models transmit behavioral traits via hidden signals in data2просмотрагод назад
Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity4просмотрагод назад
Extension OL-MDISF: Online Learning from Mix-Typed, Drifted, and Incomplete Streaming Features7просмотровгод назад
DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering16просмотровгод назад
Tree-Structured Parzen Estimator Can Solve Black-Box Combinatorial Optimization More Efficiently9просмотровгод назад
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination4просмотрагод назад
Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm4просмотрагод назад
