Related papers: SMART-Editor: A Multi-Agent Framework for Human-Li…
This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. We…
Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Existing evaluators frequently struggle with a critical…
Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional nonparametric settings with variable selection have not yet been developed. We propose a…
Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…
Tasks requiring deductive reasoning, especially those involving multiple steps, often demand adaptive strategies such as intermediate generation of rationales or programs, as no single approach is universally optimal. While Language Models…
Recent advances in text-to-image generation have produced strong single-shot models, yet no individual system reliably executes the long, compositional prompts typical of creative workflows. We introduce Image-POSER, a reflective…
Image editing has achieved impressive results with the development of large-scale generative models. However, existing models mainly focus on the editing effects of intended objects and regions, often leading to unwanted changes in…
Given an original image, image editing aims to generate an image that align with the provided instruction. The challenges are to accept multimodal inputs as instructions and a scarcity of high-quality training data, including crucial…
Multi-subject personalized image generation aims to synthesize customized images containing multiple specified subjects without requiring test-time optimization. However, achieving fine-grained independent control over multiple subjects…
Despite the remarkable capabilities of text-to-image (T2I) generation models, real-world applications often demand fine-grained, iterative image editing that existing methods struggle to provide. Key challenges include granular instruction…
Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In this paper, we rethink that the redundancy in inversion-based…
Humans naturally communicate through abstract concepts like "mood". However, current image editing benchmarks focus primarily on explicit, literal commands, leaving abstract instructions largely underexplored. In this work, we first…
Recent agentic workflows automate professional document generation but focus narrowly on textual quality, overlooking structural and stylistic professionalism, which is equally critical for readability. This gap stems mainly from a lack of…
MetaDesigner introduces a transformative framework for artistic typography synthesis, powered by Large Language Models (LLMs) and grounded in a user-centric design paradigm. Its foundation is a multi-agent system comprising the Pipeline,…
Instruction-guided 3D editing is a rapidly emerging field with the potential to broaden access to 3D content creation. However, existing methods face critical limitations: optimization-based approaches are prohibitively slow, while…
In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improving the quality and visual appeal of inpainted images.…
Instruction-guided image editing has seen remarkable progress with models like FLUX.2 and Qwen-Image-Edit, yet they still struggle with complex scenarios with multiple similar instances each requiring individual edits. We observe that…
Developers authoring HTML documents define elements following patterns which establish and reflect the visual structure of a document, such as making all images in a footer the same height by applying a class to each. To surface these…
Recent advancements in diffusion-based generative image editing have sparked a profound revolution, reshaping the landscape of image outpainting and inpainting tasks. Despite these strides, the field grapples with inherent challenges,…
Companies use banners extensively to promote their products, and the intelligent automatic synthesis of banners is a challenging event. Under the premise of inputting only a small amount of information such as product, text and size, it can…