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

Integrating Technology Acceptance Model With UTAUT to Increase the Explanatory Power of the Effect of HCI on Students’ Intention to Use E-Learning System and Perceive Success

Abstract: This study aimed to investigate the potential human-computer interaction factors (HCI) affecting students’ behavioural intentions (BI) to use the e-learning system and perceive success. This ...
IEEE

Learning Visual-Inertial Odometry With Robocentric Iterated Extended Kalman Filter

Abstract: In recent years, deep learning methodologies have been increasingly applied to the intricate challenges of visual-inertial odometry (VIO), especially in scenarios with rapid movements and ...