MIT researchers introduce VCPO (Variance Controlled Policy Optimization), a new method that improves asynchronous reinforcement learning for LLM training by addressing high variance issues in off-policy settings. The technique dynamically scales learning rates and applies variance control to achieve stable training with 2.5x speedup while maintaining performance.
MIT research reveals that leading AI chatbots deliver less accurate information to vulnerable user groups, including those with lower English proficiency, less formal education, and non-US backgrounds. The study highlights concerning disparities in AI performance that could exacerbate existing inequalities in access to reliable information.
New research from MIT's Digital Currency Initiative reveals that stablecoins face vulnerabilities beyond reserve quality issues. The study identifies additional structural weaknesses that could affect stablecoins' ability to maintain their pegs to underlying assets.
