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.
GitHub

TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling" (ICLR 2025)

This is the official repository of the paper "TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling". It consists of two parts: One dot represents a performance score on one ...
IEEE

Backdoor Attack and Defense on Deep Learning: A Survey

Abstract: Deep learning, as an important branch of machine learning, has been widely applied in computer vision, natural language processing, speech recognition, and more. However, recent studies have ...
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 ...
IEEE

GreenFlow: A Carbon-Efficient Scheduler for Deep Learning Workloads

Abstract: Deep learning (DL) has become a key component of modern software. Training DL models leads to huge carbon emissions. In data centers, it is important to reduce carbon emissions while ...