MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

MIT researchers unveil a new fine-tuning method that lets enterprises consolidate their "model zoos" into a single, continuously learning agent.
IEEE

Distributionally Robust Differential Dynamic Programming With Wasserstein Distance

Abstract: Differential dynamic programming (DDP) is a popular technique for solving nonlinear optimal control problems with locally quadratic approximations. However, existing DDP methods are not ...
GitHub

MPAX: Mathematical Programming in JAX

MPAX is a hardware-accelerated, differentiable, batchable, and distributable solver for mathematical programming in JAX, designed to integrate with modern computational and deep learning workflows: ...
IEEE

An Unknown Multiplayer Nonzero-Sum Game: Prescribed-Time Dynamic Event-Triggered Control via Adaptive Dynamic Programming

Abstract: In this paper, the novel prescribed-time dynamic event-triggered control method of an unknown multiplayer nonzero-sum game (MP-NZSG) is designed by using adaptive dynamic programming (ADP).