Ai2's new Olmo 3.1 extends reinforcement learning training for stronger reasoning benchmarks

Ai2 updates its Olmo 3 family of models to Olmo 3.1 following additional extended RL training to boost performance.
IEEE

On the Regret of Model Predictive Control With Imperfect Inputs

Abstract: Implementing model predictive control (MPC) in practice faces many subtle but prevalent problems, including modeling errors, solver errors, and actuator faults. In essence, the real control ...