2025/12/26 by Yang Ding, Yizhen Zhang, Ding, Yang +7 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Multimodal Machine Learning Applications
paper · doi:10.48550/arxiv.2512.22315
openalex publication_date 2025/12/26 · openalex created_date 2025/12/31 · openalex updated_date 2026/07/28
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language tasks yet remain limited in long video understanding due to the limited context window. Consequently, prevailing approaches tend to rely on uniform frame sampling or static pre-selection, which might overlook critical evidence and unable to correct its initial selection error during its reasoning process. To overcome these limitations, we propose VideoZoomer, a novel agentic framework that enables MLLMs to dynamically control their visual focus during reasoning. Starting from a coarse low-frame-rate overview, VideoZoomer invokes a temporal zoom tool to obtain high-frame-rate clips at autonomously chosen moments, thereby progressively gathering fine-grained evidence in a multi-turn interactive manner. Accordingly, we adopt a two-stage training strategy: a cold-start supervised fine-tuning phase on a curated dataset of distilled exemplar and reflection trajectories, followed by reinforcement learning to further refine the agentic policy. Extensive experiments demonstrate that our 7B model delivers diverse and complex reasoning patterns, yielding strong performance across a broad set of long video understanding and reasoning benchmarks. These emergent capabilities allow it to consistently surpass existing open-source models and even rival proprietary systems on challenging tasks, while achieving superior efficiency under reduced frame budgets.