12+06:44Subliminal Learning: Language models transmit behavioral traits via hidden signals in data2просмотра3 дня назад
12+07:10Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity2просмотра6 дней назад
12+06:07Extension OL-MDISF: Online Learning from Mix-Typed, Drifted, and Incomplete Streaming Features7просмотров6 дней назад
12+07:26DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering16просмотров8 дней назад
12+06:56Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety10просмотров9 дней назад
12+07:01Tree-Structured Parzen Estimator Can Solve Black-Box Combinatorial Optimization More Efficiently9просмотров9 дней назад
12+06:41Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination4просмотра10 дней назад
12+08:26Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm4просмотра11 дней назад