Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yuting, Lu, Hao, Hu, Qingyong, Wang, Yin, Yuan, Kaishen, Liu, Xin, Wu, Kaishun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913867475451904
author Zhang, Yuting
Lu, Hao
Hu, Qingyong
Wang, Yin
Yuan, Kaishen
Liu, Xin
Wu, Kaishun
author_facet Zhang, Yuting
Lu, Hao
Hu, Qingyong
Wang, Yin
Yuan, Kaishen
Liu, Xin
Wu, Kaishun
contents Periodic or quasi-periodic phenomena reveal intrinsic characteristics in various natural processes, such as weather patterns, movement behaviors, traffic flows, and biological signals. Given that these phenomena span multiple modalities, the capabilities of Multimodal Large Language Models (MLLMs) offer promising potential to effectively capture and understand their complex nature. However, current MLLMs struggle with periodic tasks due to limitations in: 1) lack of temporal modelling and 2) conflict between short and long periods. This paper introduces Period-LLM, a multimodal large language model designed to enhance the performance of periodic tasks across various modalities, and constructs a benchmark of various difficulty for evaluating the cross-modal periodic capabilities of large models. Specially, We adopt an "Easy to Hard Generalization" paradigm, starting with relatively simple text-based tasks and progressing to more complex visual and multimodal tasks, ensuring that the model gradually builds robust periodic reasoning capabilities. Additionally, we propose a "Resisting Logical Oblivion" optimization strategy to maintain periodic reasoning abilities during semantic alignment. Extensive experiments demonstrate the superiority of the proposed Period-LLM over existing MLLMs in periodic tasks. The code is available at https://github.com/keke-nice/Period-LLM.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24476
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model
Zhang, Yuting
Lu, Hao
Hu, Qingyong
Wang, Yin
Yuan, Kaishen
Liu, Xin
Wu, Kaishun
Computer Vision and Pattern Recognition
Periodic or quasi-periodic phenomena reveal intrinsic characteristics in various natural processes, such as weather patterns, movement behaviors, traffic flows, and biological signals. Given that these phenomena span multiple modalities, the capabilities of Multimodal Large Language Models (MLLMs) offer promising potential to effectively capture and understand their complex nature. However, current MLLMs struggle with periodic tasks due to limitations in: 1) lack of temporal modelling and 2) conflict between short and long periods. This paper introduces Period-LLM, a multimodal large language model designed to enhance the performance of periodic tasks across various modalities, and constructs a benchmark of various difficulty for evaluating the cross-modal periodic capabilities of large models. Specially, We adopt an "Easy to Hard Generalization" paradigm, starting with relatively simple text-based tasks and progressing to more complex visual and multimodal tasks, ensuring that the model gradually builds robust periodic reasoning capabilities. Additionally, we propose a "Resisting Logical Oblivion" optimization strategy to maintain periodic reasoning abilities during semantic alignment. Extensive experiments demonstrate the superiority of the proposed Period-LLM over existing MLLMs in periodic tasks. The code is available at https://github.com/keke-nice/Period-LLM.
title Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.24476