Related papers: Embedding Arithmetic: A Lightweight, Tuning-Free F…

Humor is a natural and fundamental component of human interactions. When correctly applied, humor allows us to express thoughts and feelings conveniently and effectively, increasing interpersonal affection, likeability, and trust. However,…

Text embedding models from Natural Language Processing can map text data (e.g. words, sentences, documents) to supposedly meaningful numerical representations (a.k.a. text embeddings). While such models are increasingly applied in social…

Text-to-image (T2I) generation has made remarkable progress in producing high-quality images, but a fundamental challenge remains: creating backgrounds that naturally accommodate text placement without compromising image quality. This…

We review the current schemes of text-image matching models and propose improvements for both training and inference. First, we empirically show limitations of two popular loss (sum and max-margin loss) widely used in training text-image…

Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications. However, since they are highly data-driven, relying on billion-sized datasets randomly…

Rectified Flow (RF) models trained with a Flow matching framework have achieved state-of-the-art performance on Text-to-Image (T2I) conditional generation. Yet, multiple benchmarks show that synthetic images can still suffer from poor…

Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply…

Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…

Text embeddings are vital for tasks such as text retrieval and semantic textual similarity (STS). Recently, the advent of pretrained language models, along with unified benchmarks like the Massive Text Embedding Benchmark (MTEB), has…

Text embeddings have become central to computational social science and psychology, enabling scalable measurement of meaning and mixed-method inference. Yet most representation learning is optimized and evaluated for prediction and…

Text-to-image models often struggle to generate images that precisely match textual prompts. Prior research has extensively studied the evaluation of image-text alignment in text-to-image generation. However, existing evaluations primarily…

Stochastic embedding transitions introduce a probabilistic mechanism for adjusting token representations dynamically during inference, mitigating the constraints imposed through static or deterministic embeddings. A transition framework was…

Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…

Concept-based approaches, which aim to identify human-understandable concepts within a model's internal representations, are a promising method for interpreting embeddings from deep neural network models, such as CLIP. While these…

In this paper, we conduct a study on the state-of-the-art methods for text-to-image synthesis and propose a framework to evaluate these methods. We consider syntheses where an image contains a single or multiple objects. Our study outlines…

The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become…

Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…

Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts. Recently, encoder-based techniques have emerged as a new effective approach…

Multimodal machine learning models, such as those that combine text and image modalities, are increasingly used in critical domains including public safety, security, and healthcare. However, these systems inherit biases from their single…

The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text…