# Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner

arXiv: https://arxiv.org/abs/2406.00432 · HTML: https://mlsanity.com/paper/2406.00432/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 66 references that are in the map.
- First posted on arXiv 1 Jun 2024.

## Builds on (most cited first, 29 of 29)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Diffusion Models already have a Semantic Latent Space](https://mlsanity.com/paper/2210.10960/) (2022)
- [Diffusion Self-Guidance for Controllable Image Generation](https://mlsanity.com/paper/2306.00986/) (2023)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [Diffusion models as plug-and-play priors](https://mlsanity.com/paper/2206.09012/) (2022)
- [DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models](https://mlsanity.com/paper/2307.02421/) (2023)
- [Guiding Instruction-based Image Editing via Multimodal Large Language Models](https://mlsanity.com/paper/2309.17102/) (2023)
- [HIVE: Harnessing Human Feedback for Instructional Visual Editing](https://mlsanity.com/paper/2303.09618/) (2023)
- [Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models](https://mlsanity.com/paper/2211.17091/) (2022)
- [LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts](https://mlsanity.com/paper/2310.10640/) (2023)
- [GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models](https://mlsanity.com/paper/2404.07206/) (2024)
- [InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser](https://mlsanity.com/paper/2311.15040/) (2023)
- [Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback](https://mlsanity.com/paper/2307.02770/) (2023)
- [Chaining text-to-image and large language model: A novel approach for generating personalized e-commerce banners](https://mlsanity.com/paper/2403.05578/) (2024)
- [Image Translation as Diffusion Visual Programmers](https://mlsanity.com/paper/2401.09742/) (2024)

## Built on by (most cited first, 8 of 8)

- [MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs](https://mlsanity.com/paper/2406.08772/) (2024)
- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search](https://mlsanity.com/paper/2505.19768/) (2025)
- [TDEdit: A Unified Diffusion Framework for Text-Drag Guided Image Manipulation](https://mlsanity.com/paper/2509.21905/) (2025)
- [RealDrag: The First Dragging Benchmark with Real Target Image](https://mlsanity.com/paper/2512.12287/) (2025)
- [DynaDrag: Dynamic Drag-Style Image Editing by Motion Prediction](https://mlsanity.com/paper/2601.00542/) (2026)
- [In-context Region-based Drag: Drag Any Region to Any Shape](https://mlsanity.com/paper/2606.25907/) (2026)
- [ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning](https://mlsanity.com/paper/2610.13316/) (2026)

## Abstract (arXiv)

Flexible and accurate drag-based editing is a challenging task that has recently garnered significant attention. Current methods typically model this problem as automatically learning "how to drag" through point dragging and often produce one deterministic estimation, which presents two key limitations: 1) Overlooking the inherently ill-posed nature of drag-based editing, where multiple results may correspond to a given input, as illustrated in Fig.1; 2) Ignoring the constraint of image quality, which may lead to unexpected distortion. To alleviate this, we propose LucidDrag, which shifts the focus from "how to drag" to "what-then-how" paradigm. LucidDrag comprises an intention reasoner and a collaborative guidance sampling mechanism. The former infers several optimal editing strategies, identifying what content and what semantic direction to be edited. Based on the former, the latter addresses "how to drag" by collaboratively integrating existing editing guidance with the newly proposed semantic guidance and quality guidance. Specifically, semantic guidance is derived by establishing a semantic editing direction based on reasoned intentions, while quality guidance is achieved through classifier guidance using an image fidelity discriminator. Both qualitative and quantitative comparisons demonstrate the superiority of LucidDrag over previous methods.