# VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning

arXiv: https://arxiv.org/abs/2506.18564 · HTML: https://mlsanity.com/paper/2506.18564/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 30 of 32)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation](https://mlsanity.com/paper/2406.15252/) (2024)
- [FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling](https://mlsanity.com/paper/2207.02595/) (2022)
- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Large-Scale Study of Perceptual Video Quality](https://mlsanity.com/paper/1803.01761/) (2018)
- [VideoDPO: Omni-Preference Alignment for Video Diffusion Generation](https://mlsanity.com/paper/2412.14167/) (2024)
- [Video Diffusion Alignment via Reward Gradients](https://mlsanity.com/paper/2407.08737/) (2024)
- [Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models](https://mlsanity.com/paper/2312.08962/) (2023)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback](https://mlsanity.com/paper/2405.18750/) (2024)
- [GenAI Arena: An Open Evaluation Platform for Generative Models](https://mlsanity.com/paper/2406.04485/) (2024)
- [Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration](https://mlsanity.com/paper/2305.14324/) (2023)
- [LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment](https://mlsanity.com/paper/2412.04814/) (2024)

## Built on by (most cited first, 26 of 26)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining](https://mlsanity.com/paper/2507.14119/) (2025)
- [Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment](https://mlsanity.com/paper/2510.11369/) (2025)
- [VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning](https://mlsanity.com/paper/2508.06051/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization](https://mlsanity.com/paper/2510.03161/) (2025)
- [UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement](https://mlsanity.com/paper/2512.06750/) (2025)
- [EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment](https://mlsanity.com/paper/2602.01173/) (2026)
- [TalkPhoto: A Versatile Training-Free Conversational Assistant for Intelligent Image Editing](https://mlsanity.com/paper/2601.01915/) (2026)
- [Q-Bench-Portrait: Benchmarking Multimodal Large Language Models on Portrait Image Quality Perception](https://mlsanity.com/paper/2601.18346/) (2026)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)
- [MDS-VQA: Model-Informed Data Selection for Video Quality Assessment](https://mlsanity.com/paper/2603.11525/) (2026)
- [OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution](https://mlsanity.com/paper/2603.12811/) (2026)
- [DRM: Diffusion-based Reward Model With Step-wise Guidance](https://mlsanity.com/paper/2605.25661/) (2026)
- [Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models](https://mlsanity.com/paper/2607.09091/) (2026)
- [PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment](https://mlsanity.com/paper/2511.05393/) (2025)
- [VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought](https://mlsanity.com/paper/2603.22998/) (2026)
- [Comparison Drives Preference: Reference-Aware Modeling for AI-Generated Video Quality Assessment](https://mlsanity.com/paper/2604.17074/) (2026)
- [VersusQ: Pairwise Margin Reasoning for Generalizable Video Quality Assessment](https://mlsanity.com/paper/2605.21130/) (2026)
- [Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding](https://mlsanity.com/paper/2606.11838/) (2026)
- [LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models](https://mlsanity.com/paper/2607.01086/) (2026)
- [CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images](https://mlsanity.com/paper/2608.05569/) (2026)
- [Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training](https://mlsanity.com/paper/2608.06125/) (2026)
- [CodecArena: Codec Quality Assessment via Visual Reinforcement Learning](https://mlsanity.com/paper/2608.09139/) (2026)
- [TryOnReward: Learning Foveated Consistency for Reinforcement Fine-Tuning of Virtual Try-On](https://mlsanity.com/paper/2609.13259/) (2026)
- [MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos](https://mlsanity.com/paper/2609.37030/) (2026)

## Abstract (arXiv)

Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited generalization, lack of temporal awareness, heavy reliance on large-scale annotated datasets, and the lack of effective interaction with generation models. Most current approaches rely on supervised finetuning of vision-language models (VLMs), which often require large-scale annotated datasets and tend to decouple understanding and generation. To address these shortcomings, we propose VQ-Insight, a novel reasoning-style VLM framework for AIGC video quality assessment. Our approach features: (1) a progressive video quality learning scheme that combines image quality warm-up, general task-specific temporal learning, and joint optimization with the video generation model; (2) the design of multi-dimension scoring rewards, preference comparison rewards, and temporal modeling rewards to enhance both generalization and specialization in video quality evaluation. Extensive experiments demonstrate that VQ-Insight consistently outperforms state-of-the-art baselines in preference comparison, multi-dimension scoring, and natural video scoring, bringing significant improvements for video generation tasks.