Figure 1: Examples of high-resolution images generated by a 2.3B U-ViT 1K model. We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0.3B upto 8B parameters on datasets up to 600M images. We find that U-ViT, a pure self-attention based DiT model provides a simpler design and scales more effectively in comparison with crossattention based DiT variants, which allows straightforward expansion for extra conditions and other modalities. We identify a 2.3B U-ViT model can get better performance than SDXL UNet and other DiT variants in controlled setting. On the data scaling side, we investigate how increasing dataset size and enhanced long caption improve the text-image alignment performance and the learning efficiency. Transformer (Vaswani et al., 2017)'s straightforward design and ability to scale efficiently has driven significant advancements in large language models (LLMs) (Kaplan et al., 2020). Its inherent simplicity and ease of parallelization makes it well-suited for hardware acceleration. Despite the rapid evolution of DiT models, a comprehensive comparison between various DiT architectures and UNet-based models for text-to-image generation (T2I) is still lacking. Furthermore, the optimal scaling strategy for transformer models in T2I tasks compared to UNet is yet to be determined. The challenge of establishing a fair comparison is further compounded by the variation in training settings and the significant computational resources required to train these models.

We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our approach enables training-free continual learning and unlearning with no additional memory or inference costs, since models corresponding to data shards can be added or removed by re-averaging. We show that Diffusion Soup samples from a point in weight space that approximates the geometric mean of the distributions of constituent datasets, which offers anti-memorization guarantees and enables zero-shot style mixing. Empirically, Diffusion Soup outperforms a paragon model trained on the union of all data shards and achieves a 30% improvement in Image Reward (.34 $\to$ .44) on domain sharded data, and a 59% improvement in IR (.37 $\to$ .59) on aesthetic data. In both cases, souping also prevails in TIFA score (respectively, 85.5 $\to$ 86.5 and 85.6 $\to$ 86.8). We demonstrate robust unlearning -- removing any individual domain shard only lowers performance by 1% in IR (.45 $\to$ .44) -- and validate our theoretical insights on anti-memorization using real data. Finally, we showcase Diffusion Soup's ability to blend the distinct styles of models finetuned on different shards, resulting in the zero-shot generation of hybrid styles.

Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing attempts to rectify this issue are hindered by the inherent limitations of the pre-trained models and fail to substantially improve demographic diversity. In this work, we introduce Fair Retrieval Augmented Generation (FairRAG), a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation. FairRAG enables conditioning through a lightweight linear module that projects reference images into the textual space. To enhance fairness, FairRAG applies simple-yet-effective debiasing strategies, providing images from diverse demographic groups during the generative process. Extensive experiments demonstrate that FairRAG outperforms existing methods in terms of demographic diversity, image-text alignment, and image fidelity while incurring minimal computational overhead during inference.

Scaling up model and data size has been quite successful for the evolution of LLMs. However, the scaling law for the diffusion based text-to-image (T2I) models is not fully explored. It is also unclear how to efficiently scale the model for better performance at reduced cost. The different training settings and expensive training cost make a fair model comparison extremely difficult. In this work, we empirically study the scaling properties of diffusion based T2I models by performing extensive and rigours ablations on scaling both denoising backbones and training set, including training scaled UNet and Transformer variants ranging from 0.4B to 4B parameters on datasets upto 600M images. For model scaling, we find the location and amount of cross attention distinguishes the performance of existing UNet designs. And increasing the transformer blocks is more parameter-efficient for improving text-image alignment than increasing channel numbers. We then identify an efficient UNet variant, which is 45% smaller and 28% faster than SDXL's UNet. On the data scaling side, we show the quality and diversity of the training set matters more than simply dataset size. Increasing caption density and diversity improves text-image alignment performance and the learning efficiency. Finally, we provide scaling functions to predict the text-image alignment performance as functions of the scale of model size, compute and dataset size.

Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous approaches augment textual dialogues with retrieved images, posing privacy, diversity, and quality constraints. In this work, we introduce \textbf{M}ultimodal \textbf{A}ugmented \textbf{G}enerative \textbf{I}mages \textbf{D}ialogues (MAGID), a framework to augment text-only dialogues with diverse and high-quality images. Subsequently, a diffusion model is applied to craft corresponding images, ensuring alignment with the identified text. Finally, MAGID incorporates an innovative feedback loop between an image description generation module (textual LLM) and image quality modules (addressing aesthetics, image-text matching, and safety), that work in tandem to generate high-quality and multi-modal dialogues. We compare MAGID to other SOTA baselines on three dialogue datasets, using automated and human evaluation. Our results show that MAGID is comparable to or better than baselines, with significant improvements in human evaluation, especially against retrieval baselines where the image database is small.

We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models. The text-VQA task requires a model to answer a question by understanding multi-modal content: text (typically from OCR) and an associated image. To the best of our knowledge, almost all previous approaches for text-VQA process a single question and its associated content to predict a single answer. In order to answer multiple questions from the same image, each question and content are fed into the model multiple times. In contrast, our proposed MQMA approach takes multiple questions and content as input at the encoder and predicts multiple answers at the decoder in an auto-regressive manner at the same time. We make several novel architectural modifications to standard encoder-decoder transformers to support MQMA. We also propose a novel MQMA denoising pre-training task which is designed to teach the model to align and delineate multiple questions and content with associated answers. MQMA pre-trained model achieves state-of-the-art results on multiple text-VQA datasets, each with strong baselines. Specifically, on OCR-VQA (+2.5%), TextVQA (+1.4%), ST-VQA (+0.6%), DocVQA (+1.1%) absolute improvements over the previous state-of-the-art approaches.

Self-supervised representation learning has seen remarkable progress in the last few years. More recently, contrastive instance learning has shown impressive results compared to its supervised learning counterparts. However, even with the ever increased interest in contrastive instance learning, it is still largely unclear why these methods work so well. In this paper, we aim to unravel some of the mysteries behind their success, which are the good practices. Through an extensive empirical analysis, we hope to not only provide insights but also lay out a set of best practices that led to the success of recent work in self-supervised representation learning.

Question answering (QA) has achieved promising progress recently. However, answering a question in real-world scenarios like the medical domain is still challenging, due to the requirement of external knowledge and the insufficient of high-quality training data. In the light of these challenges, we study the task of generating medical QA pairs in this paper. With the insight that each medical question can be considered as a sample from the latent distribution conditioned on the corresponding answer, we propose an automated medical QA pair generation framework, consisting of an unsupervised key phrase detector that explores unstructured material for validity, and a generator that involves multi-pass decoder to integrate with structural knowledge for diversity. Series of experiments have been conducted on a real-world dataset collected from the National Medical Licensing Examination of China. Both automatic evaluation and human annotation demonstrate the effectiveness of the proposed method. Further investigation shows that, by incorporating the generated QA pairs for training, significant improvement in terms of accuracy can be achieved for the examination QA system.

The emergence and ubiquity of online social networks have enriched web data with evolving interactions and communities both at mega-scale and in real-time. This data offers an unprecedented opportunity for studying the interaction between society and disease outbreaks. The challenge we describe in this data paper is how to extract and leverage epidemic outbreak insights from massive amounts of social media data and how this exercise can benefit medical professionals, patients, and policymakers alike. We attempt to prepare the research community for this challenge with four datasets. Publishing the four datasets will commoditize the data infrastructure to allow a higher and more efficient focal point for the research community.