Related papers: SIGMA: Selective-Interleaved Generation with Multi…

Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual…

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Existing EEG-driven image reconstruction methods often overlook spatial attention mechanisms, limiting fidelity and semantic coherence. To address this, we propose a dual-conditioning framework that combines EEG embeddings with spatial…

Multi-attribute conditional image generation is a challenging problem in computervision. We propose Multi-attribute Pizza Generator (MPG), a conditional Generative Neural Network (GAN) framework for synthesizing images from a trichotomy of…

How humans can effectively and efficiently acquire images has always been a perennial question. A classic solution is text-to-image retrieval from an existing database; however, the limited database typically lacks creativity. By contrast,…

In this paper, we present an efficient and effective single-stage framework (DiverGAN) to generate diverse, plausible and semantically consistent images according to a natural-language description. DiverGAN adopts two novel word-level…

Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail. However, existing text-guided diffusion models offer only coarse global control and lack the ability to enforce…

The remarkable capabilities of pretrained image diffusion models have been utilized not only for generating fixed-size images but also for creating panoramas. However, naive stitching of multiple images often results in visible seams.…

We present a novel image editing scenario termed Text-grounded Object Generation (TOG), defined as generating a new object in the real image spatially conditioned by textual descriptions. Existing diffusion models exhibit limitations of…

Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in…

Advanced diffusion models like RPG, Stable Diffusion 3 and FLUX have made notable strides in compositional text-to-image generation. However, these methods typically exhibit distinct strengths for compositional generation, with some…

Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with…

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Recent advancements in the domain of text-to-image synthesis have culminated in a multitude of enhancements pertaining to quality, fidelity, and diversity. Contemporary techniques enable the generation of highly intricate visuals which…

Synthetic data is useful only when the added samples fill missing parts of the training distribution that matter for the downstream task. We introduce LiBaGS, a lightweight, generator-agnostic method for targeted synthetic training data…

In-context image generation and editing (ICGE) enables users to specify visual concepts through interleaved image-text prompts, demanding precise understanding and faithful execution of user intent. Although recent unified multimodal models…

The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor. Compared to conventional Data Augmentation (DA) techniques (e.g. cropping and rotation), exploiting prevailing diffusion models for data…

Recent works on diffusion models have demonstrated a strong capability for conditioning image generation, e.g., text-guided image synthesis. Such success inspires many efforts trying to use large-scale pre-trained diffusion models for…

Few-shot class-incremental learning (FSCIL) is challenging due to extremely limited training data while requiring models to acquire new knowledge without catastrophic forgetting. Recent works have explored generative models, particularly…

Diffusion models dominate image editing, yet their global denoising mechanism entangles edited regions with surrounding context, causing modifications to propagate into areas that should remain intact. We propose a fundamentally different…