GitHub

verl: Volcano Engine Reinforcement Learning for LLMs

verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). verl is the open-source version of HybridFlow: A Flexible and Efficient RLHF Framework paper.
IEEE

Certificating Safety of Imitation Learning for Autonomous Driving With Learnable Weighted Control Barrier Functions

Abstract: Imitation learning is increasingly utilized to improve driving performance using real-world data, yet ensuring the safety of its outputs remains a fundamental challenge. While differentiable ...
IEEE

OPVSim: Applying a Graph-Based Methodology for VR Training in Guided Learning of Emergency Procedures in a Ship's Engineering Room

Abstract: Virtual Reality (VR) can support effective and scalable training for procedures presented as step-by-step processes in machinery use, such as in an engineering room. Currently, many ...
Microsoft

Agent Lightning: Adding reinforcement learning to AI agents without code rewrites

AI agents are reshaping software development, from writing code to carrying out complex instructions. Yet LLM-based agents are prone to errors and often perform poorly on complicated, multi-step tasks ...
in.mashable

Should You Still Learn to Code? 'Godfather Of AI' Geoffrey Hinton Has An Answer

As AI systems continue to advance and take over tasks like writing and even implementing code, many in the tech world believe that traditional coding skills may soon become obsolete. However, Geoffrey ...