Cover Image

Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yuan, Li, Ouxiang, Xu, Yulong, Liao, Borui, Liang, Jiajun, Li, Jinghan, Wang, Meng, Wang, Xintao, Wan, Pengfei, Liu, Kuien, Wang, Xiang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model
by: Wang, Yuan, et al.
Published: (2026)

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
by: Wang, Qunzhong, et al.
Published: (2025)

Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
by: Wang, Yuan, et al.
Published: (2024)

Analytic Score Optimization for Multi Dimension Video Quality Assessment
by: Lin, Boda, et al.
Published: (2026)

Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring
by: Huang, Youhan, et al.
Published: (2026)

Rethinking Reward Signals in Video GRPO: When Scores Become Targets
by: Li, Rui, et al.
Published: (2025)

GARDO: Reinforcing Diffusion Models without Reward Hacking
by: He, Haoran, et al.
Published: (2025)

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
by: Li, Ouxiang, et al.
Published: (2025)

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
by: Hu, Pengfei, et al.
Published: (2025)

VideoScore2: Think before You Score in Generative Video Evaluation
by: He, Xuan, et al.
Published: (2025)

Scaling Image and Video Generation via Test-Time Evolutionary Search
by: He, Haoran, et al.
Published: (2025)

Geometry-Aware Implicit Memory for Video World Models
by: Wei, Zhengxuan, et al.
Published: (2026)

A Reason-then-Describe Instruction Interpreter for Controllable Video Generation
by: Wu, Shengqiong, et al.
Published: (2025)

Reinforcing Video Reasoning with Focused Thinking
by: Dang, Jisheng, et al.
Published: (2025)

UniVideo: Unified Understanding, Generation, and Editing for Videos
by: Wei, Cong, et al.
Published: (2025)

EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling
by: Luo, Xin, et al.
Published: (2025)

StyleMaster: Stylize Your Video with Artistic Generation and Translation
by: Ye, Zixuan, et al.
Published: (2024)

GameFactory: Creating New Games with Generative Interactive Videos
by: Yu, Jiwen, et al.
Published: (2025)

Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR
by: Lu, Jinda, et al.
Published: (2026)

PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution
by: Du, Shian, et al.
Published: (2025)

End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling
by: Liang, Jianxin, et al.
Published: (2024)

Thinking with Spatial Code for Physical-World Video Reasoning
by: Chen, Jieneng, et al.
Published: (2026)

Target-Balanced Score Distillation
by: Xu, Zhou, et al.
Published: (2025)

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
by: Cheng, Junhao, et al.
Published: (2025)

RelightMaster: Precise Video Relighting with Multi-plane Light Images
by: Bian, Weikang, et al.
Published: (2025)

VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning
by: Wang, Zikang, et al.
Published: (2025)

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
by: Wang, Qinghe, et al.
Published: (2025)

Bad Seeing or Bad Thinking? Rewarding Perception for Vision-Language Reasoning
by: Wang, Haozhe, et al.
Published: (2026)

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning
by: Huang, Yuzhou, et al.
Published: (2025)

FullDiT: Multi-Task Video Generative Foundation Model with Full Attention
by: Ju, Xuan, et al.
Published: (2025)

SketchVideo: Sketch-based Video Generation and Editing
by: Liu, Feng-Lin, et al.
Published: (2025)

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
by: Yang, Zhenhao, et al.
Published: (2026)

Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control
by: Fu, Xiao, et al.
Published: (2025)

Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
by: Li, Jinghan, et al.
Published: (2026)

HumanScore: Benchmarking Human Motions in Generated Videos
by: Fang, Yusu, et al.
Published: (2026)

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
by: Li, Ouxiang, et al.
Published: (2025)

Decoupled Functional Evaluation of Autonomous Driving Models via Feature Map Quality Scoring
by: Zhang, Ludan, et al.
Published: (2025)

CrossScore: Towards Multi-View Image Evaluation and Scoring
by: Wang, Zirui, et al.
Published: (2024)

Flow-GRPO: Training Flow Matching Models via Online RL
by: Liu, Jie, et al.
Published: (2025)

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution
by: Du, Shian, et al.
Published: (2025)