Related papers: OmniStyle: Filtering High Quality Style Transfer D…

We address the problem of ensemble selection in transfer learning: Given a large pool of source models we want to select an ensemble of models which, after fine-tuning on the target training set, yields the best performance on the target…

Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs). Despite the rapid progression of open-source LMMs, there remains a pronounced…

Personalized outfit recommendation remains a complex challenge, demanding both fashion compatibility understanding and trend awareness. This paper presents a novel framework that harnesses the expressive power of large language models…

To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve…

While multi-modality large language models excel in object-centric or indoor scenarios, scaling them to 3D city-scale environments remains a formidable challenge. To bridge this gap, we propose 3DCity-LLM, a unified framework designed for…

While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as their backbone, leaving significant room to explore effective and efficient…

Text style transfer is usually performed using attributes that can take a handful of discrete values (e.g., positive to negative reviews). In this work, we introduce an architecture that can leverage pre-trained consistent continuous…

Style transfer is to render given image contents in given styles, and it has an important role in both computer vision fundamental research and industrial applications. Following the success of deep learning based approaches, this problem…

Text Style Transfer (TST) seeks to alter the style of text while retaining its core content. Given the constraints of limited parallel datasets for TST, we propose CoTeX, a framework that leverages large language models (LLMs) alongside…

While large-scale diffusion models have revolutionized video synthesis, achieving precise control over both multi-subject identity and multi-granularity motion remains a significant challenge. Recent attempts to bridge this gap often suffer…

Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy…

Given an arbitrary content and style image, arbitrary style transfer aims to render a new stylized image which preserves the content image's structure and possesses the style image's style. Existing arbitrary style transfer methods are…

Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images,…

Prior approaches injecting camera control into diffusion models have focused on specific subsets of 4D consistency tasks: novel view synthesis, text-to-video with camera control, image-to-video, amongst others. Therefore, these fragmented…

Cell microscopy data are abundant; however, corresponding segmentation annotations remain scarce. Moreover, variations in cell types, imaging devices, and staining techniques introduce significant domain gaps between datasets. As a result,…

Style transfer is a problem of rendering image with some content in the style of another image, for example a family photo in the style of a painting of some famous artist. The drawback of classical style transfer algorithm is that it…

Recent research on representation learning has proved the merits of multi-modal clues for robust semantic segmentation. Nevertheless, a flexible pretrain-and-finetune pipeline for multiple visual modalities remains unexplored. In this…

Large Language Models drive a wide range of modern AI applications but impose substantial challenges on large-scale serving systems due to intensive computation, strict latency constraints, and throughput bottlenecks. We introduce…

Style transfer is the task of rewriting a sentence into a target style while approximately preserving content. While most prior literature assumes access to a large style-labelled corpus, recent work (Riley et al. 2021) has attempted…

Stylization for visual content aims to add specific style patterns at the pixel level while preserving the original structural features. Compared with using predefined styles, stylization guided by reference style images is more…