VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Zengjie, Qiu, Jiantao, Bai, Tianyi, Yang, Haojin, Yuan, Binhang, Jing, Qi, He, Conghui, Zhang, Wentao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!