Related papers: Style2Code: A Style-Controllable Code Generation F…

Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language…

Style transfer must match a target style while preserving content semantics. DiT-based diffusion models often suffer from content-style entanglement, leading to reference-content leakage and unstable generation. We present UniCSG, a unified…

Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via…

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the…

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ…

Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to…

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…

In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high-quality artistic faces with diverse styles and…

Discovering meaningful directions in the latent space of GANs to manipulate semantic attributes typically requires large amounts of labeled data. Recent work aims to overcome this limitation by leveraging the power of Contrastive…

Artistic text style transfer is the task of migrating the style from a source image to the target text to create artistic typography. Recent style transfer methods have considered texture control to enhance usability. However, controlling…

We explore the idea of compressing the prompts used to condition language models, and show that compressed prompts can retain a substantive amount of information about the original prompt. For severely compressed prompts, while fine-grained…

While Vision Language Models (VLMs) have shown promise in Design-to-Code generation, they suffer from a "holistic bottleneck-failing to reconcile high-level structural hierarchy with fine-grained visual details, often resulting in layout…

Current text conditioned image generation methods output realistic looking images, but they fail to capture specific styles. Simply finetuning them on the target style datasets still struggles to grasp the style features. In this work, we…

This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to…

We present the Melody-Guided Music Generation (MG2) model, a novel approach using melody to guide the text-to-music generation that, despite a simple method and limited resources, achieves excellent performance. Specifically, we first align…

This paper presents an expressive speech synthesis architecture for modeling and controlling the speaking style at a word level. It attempts to learn word-level stylistic and prosodic representations of the speech data, with the aid of two…

Large Language Models (LLMs) have shown outstanding breakthroughs in code generation. Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs, which can be challenging to scale due to the dependence on a…

Generating high-quality and diverse human images is an important yet challenging task in vision and graphics. However, existing generative models often fall short under the high diversity of clothing shapes and textures. Furthermore, the…