Related papers: MIRAGE: Benchmarking and Aligning Multi-Instance I…
Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing…
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…
While Instruction-based Image Editing (IIE) has achieved significant progress, existing benchmarks pursue task breadth via mixed evaluations. This paradigm obscures a critical failure mode crucial in professional applications: the…
Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the diverse requirements of real-world scenarios. To bridge this…
Instruction-following is a foundational capability of large language models (LLMs), with its improvement hinging on scalable and accurate feedback from judge models. However, the reliability of current judge models in instruction-following…
Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations are truly aligned across modalities. To investigate this…
Referring Image Segmentation (RIS) aims to segment an object described in natural language from an image, with the main challenge being a text-to-pixel correlation. Previous methods typically rely on single-modality features, such as vision…
We introduce MIA-Bench, a new benchmark designed to evaluate multimodal large language models (MLLMs) on their ability to strictly adhere to complex instructions. Our benchmark comprises a diverse set of 400 image-prompt pairs, each crafted…
Image spatial editing performs geometry-driven transformations, allowing precise control over object layout and camera viewpoints. Current models are insufficient for fine-grained spatial manipulations, motivating a dedicated assessment…
With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most…
Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the edited region with the entire image context, leading to…
Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining…
Recent multimodal image generators such as GPT-4o, Gemini 2.0 Flash, and Gemini 2.5 Pro excel at following complex instructions, editing images and maintaining concept consistency. However, they are still evaluated by disjoint toolkits:…
In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive manner through natural language instructions. However, an important yet underexplored research…
Language-driven image editing can significantly save the laborious image editing work and be friendly to the photography novice. However, most similar work can only deal with a specific image domain or can only do global retouching. To…
Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…
We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is trained using pseudo-MOS (Mean Opinion Score) supervision, in…
Although recent years have witnessed significant advancements in image editing thanks to the remarkable progress of text-to-image diffusion models, the problem of non-rigid image editing still presents its complexities and challenges.…
While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and utility. A small but growing line of research has explored tools and processes to better…
Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning,…