The Role of Entropy in Visual Grounding: Analysis and Optimization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Shuo, Sun, Jiajun, Zhang, Zhihao, Fan, Xiaoran, Jin, Senjie, Li, Hui, Yang, Yuming, Ye, Junjie, Shen, Lixing, Ji, Tao, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918236006645760
author Li, Shuo
Sun, Jiajun
Zhang, Zhihao
Fan, Xiaoran
Jin, Senjie
Li, Hui
Yang, Yuming
Ye, Junjie
Shen, Lixing
Ji, Tao
Gui, Tao
Zhang, Qi
Huang, Xuanjing
author_facet Li, Shuo
Sun, Jiajun
Zhang, Zhihao
Fan, Xiaoran
Jin, Senjie
Li, Hui
Yang, Yuming
Ye, Junjie
Shen, Lixing
Ji, Tao
Gui, Tao
Zhang, Qi
Huang, Xuanjing
contents Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of various entropy control techniques. However, the role and characteristics of entropy in perception-oriented tasks like visual grounding, as well as effective strategies for controlling it, remain largely unexplored. To address this issue, we focus on the visual grounding task and analyze the role and characteristics of entropy in comparison to reasoning tasks. Building on these findings, we introduce ECVGPO (Entropy Control Visual Grounding Policy Optimization), an interpretable algorithm designed for effective entropy regulation. Through entropy control, the trade-off between exploration and exploitation is better balanced. Experiments show that ECVGPO achieves broad improvements across various benchmarks and models.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06726
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Role of Entropy in Visual Grounding: Analysis and Optimization
Li, Shuo
Sun, Jiajun
Zhang, Zhihao
Fan, Xiaoran
Jin, Senjie
Li, Hui
Yang, Yuming
Ye, Junjie
Shen, Lixing
Ji, Tao
Gui, Tao
Zhang, Qi
Huang, Xuanjing
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of various entropy control techniques. However, the role and characteristics of entropy in perception-oriented tasks like visual grounding, as well as effective strategies for controlling it, remain largely unexplored. To address this issue, we focus on the visual grounding task and analyze the role and characteristics of entropy in comparison to reasoning tasks. Building on these findings, we introduce ECVGPO (Entropy Control Visual Grounding Policy Optimization), an interpretable algorithm designed for effective entropy regulation. Through entropy control, the trade-off between exploration and exploitation is better balanced. Experiments show that ECVGPO achieves broad improvements across various benchmarks and models.
title The Role of Entropy in Visual Grounding: Analysis and Optimization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2512.06726