CVPR Findings2026
VIDEOP2R: Video Understanding from Perception to Reasoning
Yifan Jiang, Yueying Wang, Rui Zhao, Toufiq Parag, Zhimin Chen, Zhenyu Liao, Jayakrishnan Unnikrishnan
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, processaware 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale cites Training language models to follow instructions with human feedback
- On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Let's Verify Step by Step cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Let's Verify Step by Step cites Training language models to follow instructions with human feedback
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Training language models to follow instructions with human feedback
Cited by top-tier papers2
Builds on32
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards et al.ICLR 2024 · 3,045 citations
- DAPO: An Open-Source LLM Reinforcement Learning System at ScaleQiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan et al.NeurIPS 2025 · 2,828 citations
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human PreferenceWei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos et al.ICML 2024 · 1,212 citations
Related papers
- VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-TuningQi (Cheems) Wang, Yanrui Yu, Ye Yuan, Rui Mao et al.NeurIPS 2025 · 103 citations
- Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-ThoughtChao Huang, Benfeng Wang, Wei Wang, Jie Wen et al.NeurIPS 2025 · 30 citations
- Reinforcing Structured Chain-of-Thought for Video UnderstandingPeiyao Wang, Haotian Xu, Noranart Vesdapunt, Rui Hou et al.CVPR 2026 · 1 citation
- Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language ModelsHuajie Tan, Yuheng Ji, Xiaoshuai Hao, Xiansheng Chen et al.NeurIPS 2025 · 45 citations
- 3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene UnderstandingXiongkun Linghu, Jiangyong Huang, Baoxiong Jia, Siyuan HuangICML 2026 · 1 citation
