5,528,459 AI resources indexedWorking toward the world’s largest AI resource index.

PDF

TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning

Research paper by Xingjian Zhang and collaborators. Published 2025-04-13. Topics: large multimodal models, reinforcement learning, small-scale models, general question-answering datasets, video understanding model.

Resource information

Authors
Xingjian Zhang, Siwei Wen, Wenjun Wu, Lei Huang
Research area
Computer vision
Application domain
General AI research
AI methods
Reinforcement learning
Research topics
cs.CV
arXiv record date
2025-04-13
Publication date
2025-04-13
Publication
arXiv
Upstream last modified
Apr 15, 2025
Last record update
Nov 3, 2026

Abstract

Recently, improving the reasoning ability of large multimodal models (LMMs) through reinforcement learning has made great progress. However, most existing works are based on highly reasoning-intensive datasets such as mathematics and code, and researchers generally choose large-scale models as the foundation. We argue that exploring small-scale models' reasoning capabilities remains valuable for researchers with limited computational resources. Moreover, enabling models to explain their reasoning processes on general question-answering datasets is equally meaningful. Therefore, we present the small-scale video reasoning model TinyLLaVA-Video-R1. Based on TinyLLaVA-Video, a traceably trained video understanding model with no more than 4B parameters, it not only demonstrates significantly improved reasoning and thinking capabilities after using reinforcement learning on general Video-QA datasets, but also exhibits the emergent characteristic of "aha moments". Furthermore, we share a series of experimental findings, aiming to provide practical insights for future exploration of video reasoning (thinking) abilities in small-scale models. It is available at https://github.com/ZhangXJ199/TinyLLaVA-Video-R1.