Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing

arXiv:2609.36755 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/2U1/Qwen-VL-Series-Finetune3https:

Terminology

• Region-Aware Recomposition — 12× in this paper
• Generation-Stage Adaptive Conditioning — 10× in this paper
• Grounding — 10× in this paper · explained in 3 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Alignment — 9× in this paper · explained in 1 episode
• Consistency — 9× in this paper · explained in 3 episodes
• Diffusion Model — 9× in this paper · explained in 8 episodes
• Diffusion Models — 8× in this paper · explained in 6 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Latent Space — 4× in this paper · explained in 7 episodes
• Ablation — 3× in this paper · explained in 1 episode
• LoRA Adaptation — 3× in this paper · explained in 2 episodes
• Prompt Following — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Concept Preservation — 2× in this paper
• Flow Matching — 2× in this paper · explained in 8 episodes
• GRPO — 2× in this paper · explained in 6 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• LoRA Adapters — 2× in this paper · explained in 3 episodes
• Mean Distance — 2× in this paper
• Optical Flow — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment Scores — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Image Fidelity — 1× in this paper
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
• OmniGen2: Towards Instruction-Aligned Multimodal Generation
• DanceGRPO: Unleashing GRPO on Visual Generation
• Flow-GRPO: Training Flow Matching Models via Online RL
• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• LongCat-Image Technical Report
• Step1X-Edit: A Practical Framework for General Image Editing
• AdaptiveDrag: Semantic-Driven Dragging on Diffusion-Based Image Editing
• FireRed-Image-Edit-1.0 Technical Report
• LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
• DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
• ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions
• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
• Qwen2.5-VL Technical Report

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