Cover Image

VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cong, Xiaoyan, Yang, Haotian, Wang, Angtian, Wang, Yizhi, Yang, Yiding, Zhang, Canyu, Ma, Chongyang
Format:	Preprint
Published:	2025
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

ATI: Any Trajectory Instruction for Controllable Video Generation
by: Wang, Angtian, et al.
Published: (2025)

CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance
by: Deng, Yufan, et al.
Published: (2025)

HECTOR: Hybrid Editable Compositional Object References for Video Generation
by: Zhang, Guofeng, et al.
Published: (2026)

TGT: Text-Grounded Trajectories for Locally Controlled Video Generation
by: Zhang, Guofeng, et al.
Published: (2025)

MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
by: Deng, Yufan, et al.
Published: (2025)

Envision: Embodied Visual Planning via Goal-Imagery Video Diffusion
by: Gu, Yuming, et al.
Published: (2025)

InstructAV2AV: Instruction-Guided Audio-Video Joint Editing
by: Zheng, Haojie, et al.
Published: (2026)

BaseReward: A Strong Baseline for Multimodal Reward Model
by: Zhang, Yi-Fan, et al.
Published: (2025)

SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
by: Zhang, Xinyao, et al.
Published: (2026)

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
by: Chen, Yinan, et al.
Published: (2025)

LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing
by: Wang, Weicheng, et al.
Published: (2026)

OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
by: He, Haoyang, et al.
Published: (2025)

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
by: Bai, Qingyan, et al.
Published: (2025)

Guiding Instruction-based Image Editing via Multimodal Large Language Models
by: Fu, Tsu-Jui, et al.
Published: (2023)

FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space
by: FSVideo Team, et al.
Published: (2026)

Multi-Reward as Condition for Instruction-based Image Editing
by: Gu, Xin, et al.
Published: (2024)

InstructVEdit: A Holistic Approach for Instructional Video Editing
by: Zhang, Chi, et al.
Published: (2025)

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
by: Wu, Keming, et al.
Published: (2025)

Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
by: Liu, Gongye, et al.
Published: (2026)

Instruction Guided Multi Object Image Editing with Quantity and Layout Consistency
by: Tan, Jiaqi, et al.
Published: (2025)

ESA: Energy-Based Shot Assembly Optimization for Automatic Video Editing
by: Chen, Yaosen, et al.
Published: (2025)

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
by: Lin, Hangyu, et al.
Published: (2026)

AnchorSync: Global Consistency Optimization for Long Video Editing
by: Liu, Zichi, et al.
Published: (2025)

MGIMM: Multi-Granularity Instruction Multimodal Model for Attribute-Guided Remote Sensing Image Detailed Description
by: Yang, Cong, et al.
Published: (2024)

Semantic Flow: Learning Semantic Field of Dynamic Scenes from Monocular Videos
by: Tian, Fengrui, et al.
Published: (2024)

DreamVE: Unified Instruction-based Image and Video Editing
by: Xia, Bin, et al.
Published: (2025)

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
by: He, Lehan, et al.
Published: (2024)

Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models
by: Qiu, Weijie, et al.
Published: (2026)

Text-Driven Diverse Facial Texture Generation via Progressive Latent-Space Refinement
by: Wang, Chi, et al.
Published: (2024)

Neural Video Fields Editing
by: Yang, Shuzhou, et al.
Published: (2023)

Chameleon: Benchmarking Detection and Backtracking on Commercial-Grade AI-Generated Videos
by: Liao, Xingming, et al.
Published: (2025)

FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
by: Cai, Kaitong, et al.
Published: (2025)

Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
by: Liu, Yang, et al.
Published: (2025)

HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing
by: Bai, Jinbin, et al.
Published: (2024)

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

VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions
by: Wang, Ziteng, et al.
Published: (2025)

Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
by: Wang, Xingrui, et al.
Published: (2024)

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
by: Bai, Xuehai, et al.
Published: (2026)

ZONE: Zero-Shot Instruction-Guided Local Editing
by: Li, Shanglin, et al.
Published: (2023)

Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing
by: Yeh, Chun-Hsiao, et al.
Published: (2025)