ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing

arXiv:2609.38541 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://correr-zhou.github.io/ThinkV2V

Terminology

• Benchmark — 30× in this paper · explained in 2 episodes
• Consistency — 12× in this paper · explained in 3 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Alignment — 8× in this paper · explained in 1 episode
• Causal Reasoning — 8× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Iterative Refinement — 2× in this paper · explained in 3 episodes
• Temporal Flickering — 2× in this paper
• Adaptation — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Chain-of-Thought (CoT) Reasoning — 1× in this paper · explained in 2 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Latent Reasoning — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models
• OmniGen2: Towards Instruction-Aligned Multimodal Generation
• HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
• Qwen-Image Technical Report
• OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
• Omni-Video: Democratizing Unified Video Understanding and Generation
• OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
• UniVideo: Unified Understanding, Generation, and Editing for Videos
• SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
• An Empirical Study of GPT-4o Image Generation Capabilities
• In-Context Learning with Unpaired Clips for Instruction-based Video Editing
• Qwen3-VL Technical Report
• Wan: Open and Advanced Large-Scale Video Generative Models
• ImgEdit: A Unified Image Editing Dataset and Benchmark
• Step1X-Edit: A Practical Framework for General Image Editing
• X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning
• InstructX: Towards Unified Visual Editing with MLLM Guidance
• Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
• SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models