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

Aligning Crowd-Sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models

Abstract: This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, ...
IEEE

IGU-Aug: Information-Guided Unsupervised Augmentation and Pixel-Wise Contrastive Learning for Medical Image Analysis

Abstract: Contrastive learning (CL) is a form of self-supervised learning and has been widely used for various tasks. Different from widely studied instance-level contrastive learning, pixel-wise ...
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 ...
Mint

Should you still learn to code? Godfather of AI says says don’t give up on computer science degree just yet

With the rise of artificial intelligence, there has been a growing belief in the tech industry that coding will soon become redundant, given that new AI models are getting better not just at writing ...