VIDEOP2R: Video Understanding from Perception to Reasoning

Yifan Jiang; Yueying Wang; Rui Zhao; Toufiq Parag; Zhimin Chen; Zhenyu Liao; Jayakrishnan Unnikrishnan

返回文献探索

Paper · arXiv 2511.11113

VIDEOP2R: Video Understanding from Perception to Reasoning

Yifan Jiang, Yueying Wang, Rui Zhao, Toufiq Parag, Zhimin Chen, Zhenyu Liao, Jayakrishnan Unnikrishnan

113 upvotesNovember 14, 2025arXiv 预印本

AI 摘要

VideoP2R, a process-aware reinforcement fine-tuning framework, improves video reasoning and understanding by modeling perception and reasoning separately, achieving state-of-the-art results on multiple benchmarks.

Reinforcement fine-tuningsupervised fine-tuningreinforcement learninglarge language modelslarge video language modelsVideoP2RperceptionreasoningVideoP2R-CoT-162Kchain-of-thoughtprocess-aware group relative policy optimizationPA-GRPO

Abstract

Reinforcement fine-tuning (RFT), a two-stage framework consisting of supervised fine-tuning (SFT) and reinforcement learning (RL) has shown promising results on improving reasoning ability of large language models (LLMs). Yet extending RFT to large video language models (LVLMs) remains challenging. We propose VideoP2R, a novel process-aware video RFT framework that enhances video reasoning by modeling perception and reasoning as distinct processes. In the SFT stage, we develop a three-step pipeline to generate VideoP2R-CoT-162K, a high-quality, process-aware chain-of-thought (CoT) dataset for perception and reasoning. In the RL stage, we introduce a novel process-aware group relative policy optimization (PA-GRPO) algorithm that supplies separate rewards for perception and reasoning. Extensive experiments show that VideoP2R achieves state-of-the-art (SotA) performance on six out of seven video reasoning and understanding benchmarks. Ablation studies further confirm the effectiveness of our process-aware modeling and PA-GRPO and demonstrate that model's perception output is information-sufficient for downstream reasoning.