Related papers: GIVT: Generative Infinite-Vocabulary Transformers

Recent advances in generative image compression (GIC) have delivered remarkable improvements in perceptual quality. However, many GICs rely on large-scale and rigid models, which severely constrain their utility for flexible transmission…

We tackle the task of synthesizing novel views of an object given a few input images and associated camera viewpoints. Our work is inspired by recent 'geometry-free' approaches where multi-view images are encoded as a (global) set-latent…

Deep generative models have significantly advanced medical imaging analysis by enhancing dataset size and quality. Beyond mere data augmentation, our research in this paper highlights an additional, significant capacity of deep generative…

In the evolving landscape of 6G networks, semantic communications are poised to revolutionize data transmission by prioritizing the transmission of semantic meaning over raw data accuracy. This paper presents a Vision Transformer…

Diffusion Denoising Probability Models (DDPM) and Vision Transformer (ViT) have demonstrated significant progress in generative tasks and discriminative tasks, respectively, and thus far these models have largely been developed in their own…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models…

We introduce the Visual Implicit Geometry Transformer (ViGT), an autonomous driving geometric model that estimates continuous 3D occupancy fields from surround-view camera rigs. ViGT represents a step towards foundational geometric models…

Advances in GPT-based large language models (LLMs) are revolutionizing natural language processing, exponentially increasing its use across various domains. Incorporating uni-directional attention, these autoregressive LLMs can generate…

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component…

This paper presents a Generative RegIon-to-Text transformer, GRiT, for object understanding. The spirit of GRiT is to formulate object understanding as <region, text> pairs, where region locates objects and text describes objects. For…

Modern sentence encoders are used to generate dense vector representations that capture the underlying linguistic characteristics for a sequence of words, including phrases, sentences, or paragraphs. These kinds of representations are ideal…

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Generative adversarial networks (GANs) are a powerful framework for generative tasks. However, they are difficult to train and tend to miss modes of the true data generation process. Although GANs can learn a rich representation of the…

Generative joint source-channel coding (GJSCC) has emerged as a new Deep JSCC paradigm for achieving high-fidelity and robust image transmission under extreme wireless channel conditions, such as ultra-low bandwidth and low signal-to-noise…

Deepfakes have raised significant concerns due to their potential to spread false information and compromise digital media integrity. Current deepfake detection models often struggle to generalize across a diverse range of deepfake…

In this paper, we have developed a general-purpose architecture, Vit-Gan, capable of performing most of the image-to-image translation tasks from semantic image segmentation to single image depth perception. This paper is a follow-up paper,…

Volumetric visualization has long been dominated by Direct Volume Rendering (DVR), which operates on dense voxel grids and suffers from limited scalability as resolution and interactivity demands increase. Recent advances in 3D Gaussian…

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method…

In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specific design, and do…