NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Longtian, Ning, Shan, Sun, Jiaxuan, He, Xuming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!