Related papers: Language Model Beats Diffusion -- Tokenizer is Key…

There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from texts, image editing, and customized generation. We present a…

This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant…

Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual…

This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete…

Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…

One critical prerequisite for faithful text-to-image generation is the accurate understanding of text inputs. Existing methods leverage the text encoder of the CLIP model to represent input prompts. However, the pre-trained CLIP model can…

In this work, we reveal the limitations of visual tokenizers and VAEs in preserving fine-grained features, and propose a benchmark to evaluate reconstruction performance for two challenging visual contents: text and face. Visual tokenizers…

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we…

Over the past few years, Text-to-Image (T2I) generation approaches based on diffusion models have gained significant attention. However, vanilla diffusion models often suffer from spelling inaccuracies in the text displayed within the…

Text-to-video generation poses significant challenges due to the inherent complexity of video data, which spans both temporal and spatial dimensions. It introduces additional redundancy, abrupt variations, and a domain gap between language…

To build scalable models for challenging real-world tasks, it is important to learn from diverse, multi-modal data in various forms (e.g., videos, text, and images). Among the existing works, a plethora of them have focused on leveraging…

Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset.…

Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…

While diffusion models have shown impressive performance in 2D image/video generation, diffusion-based Text-to-Multi-view-Video (T2MVid) generation remains underexplored. The new challenges posed by T2MVid generation lie in the lack of…

In the realm of vision models, the primary mode of representation is using pixels to rasterize the visual world. Yet this is not always the best or unique way to represent visual content, especially for designers and artists who depict the…

The vocabulary used by language models (LM) - defined by the tokenizer - plays a key role in text generation quality. However, its impact remains under-explored in radiology. In this work, we address this gap by systematically comparing…

The development of Multi-modal Large Language Models (MLLMs) enhances Large Language Models (LLMs) with the ability to perceive data formats beyond text, significantly advancing a range of downstream applications, such as visual question…