mlsanityData to 7 Oct 2026

VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing

arXiv 2607.22632 ↗First posted 19 Jun 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The rapid rise of vlogs as a personalized storytelling medium has created a demand for automated systems to evaluate and refine vlog editing plans. However, vlog assessment is highly subjective and remains challenging due to a lack of standardized criteria, dataset and benchmark, and effective reward models. To address these challenges, we define a comprehensive vlog evaluation framework guided by professional vlog creators and product managers, establishing a taxonomy of six key dimensions, i.e., Creativity, Consistency, Concept Design, Cinematography, Narration, and Pacing. Subsequently, we curate a large-scale dataset of 100k vlog edits and a dedicated benchmark, VRMBench, to evaluate the vlog rewarding capabilities of Multimodal Large Language Models (MLLMs). Finally, we present VlogReward, a robust vlog reward model that can provide both fine-grained multi-dimensional scores and actionable feedback for iterative refinement. Technically, we enhance the Group Relative Policy Optimization (GRPO) framework by introducing an adjustable inter-group comparison reward, which mitigates the "direction blindness" issue of standard GRPO and enables the model to better distinguish varied-quality edits. VlogReward achieves state-of-the-art results that significantly outperform existing MLLMs, including GPT-5 and Gemini-3-Pro. We hope that our study can help vlog creators and foster automated vlog evaluation and refinement systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 56 references that are in the map. First posted on arXiv 19 Jun 2026.

Builds on

44 of 56 references.

References · 44

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  7. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  8. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  9. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,375
  10. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  11. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  12. 2025OpenAI GPT-5 System Cardcited by 910
32 more
  1. 2025Group Sequence Policy Optimizationcited by 788
  2. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  3. 2025VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understandingcited by 502
  4. 2023UltraFeedback: Boosting Language Models with Scaled AI Feedbackcited by 394
  5. 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 388
  6. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 284
  7. 2025Improving Video Generation with Human Feedbackcited by 267
  8. 2023Video Understanding with Large Language Models: A Surveycited by 203
  9. 2025Unified Reward Model for Multimodal Understanding and Generationcited by 194
  10. 2025RM-R1: Reward Modeling as Reasoningcited by 149
  11. 2025VisualPRM: An Effective Process Reward Model for Multimodal Reasoningcited by 134
  12. 2025Geometric-Mean Policy Optimizationcited by 107
  13. 2025Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuningcited by 86
  14. 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignmentcited by 79
  15. 2025InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Modelcited by 73
  16. 2025R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learningcited by 65
  17. 2025RewardDance: Reward Scaling in Visual Generationcited by 63
  18. 2025Reward Reasoning Modelcited by 47
  19. 2024Foundation Models for Video Understanding: A Surveycited by 46
  20. 2025BNPO: Beta Normalization Policy Optimizationcited by 28
  21. 2025EditDuet: A Multi-Agent System for Video Non-Linear Editingcited by 16
  22. 2025BaseReward: A Strong Baseline for Multimodal Reward Modelcited by 15
  23. 2025Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learningcited by 11
  24. 2025Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theorycited by 10
  25. 2024A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Modelcited by 8
  26. 2025From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understandingcited by 6
  27. 2024Generative Timelines for Instructed Visual Assemblycited by 5
  28. 2025VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understandingcited by 5
  29. 2023Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Moviescited by 4
  30. 2024Agent-based Video Trimmingcited by 4
  31. 2025GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learningcited by 4
  32. 2025GRPOformer: Advancing Hyperparameter Optimization via Group Relative Policy Optimizationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction
  2. 2024VCoME: Verbal Video Composition with Multimodal Editing Effects
  3. 2025Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models
  4. 2026Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
  5. 2026VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
  6. 2024Vlogger: Make Your Dream A Vlog
  7. 2026WorldReward: Reward Modeling for Camera-Conditioned World Models
  8. 2024Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward