Related papers: Decoder-Only LLMs are Better Controllers for Diffu…

This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims…

Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling…

Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of large-scale pre-trained language models on machine translation…

Diffusion models have demonstrated exceptional capabilities in generating a broad spectrum of visual content, yet their proficiency in rendering text is still limited: they often generate inaccurate characters or words that fail to blend…

Recent advancements in text-to-image generation have revolutionized numerous fields, including art and cinema, by automating the generation of high-quality, context-aware images and video. However, the utility of these technologies is often…

In this work, we investigate the potential of a large language model (LLM) to directly comprehend visual signals without the necessity of fine-tuning on multi-modal datasets. The foundational concept of our method views an image as a…

Masked diffusion language models (dLMs) generate text through bidirectional denoising, yet this capability remains locked for infilling prompts. This limitation is an artifact of the current supervised finetuning (SFT) convention of…

Recent Large View Synthesis Models (LVSMs) advocate an encoder-decoder architecture that separates reconstruction and rendering into distinct networks. We re-examine this design. Through controlled experiments, we show that a decoder-only…

Recently, the multimedia community has witnessed the rise of diffusion models trained on large-scale multi-modal data for visual content creation, particularly in the field of text-to-image generation. In this paper, we propose a new task…

Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion. To address these…

Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers…

Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models.…

In recent years, diffusion models have become one of the main methods for generating images. However, detecting images generated by these models remains a challenging task. This paper proposes a novel method for detecting images generated…

Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the…

In this paper, we study the problem of text line recognition. Unlike most approaches targeting specific domains such as scene-text or handwritten documents, we investigate the general problem of developing a universal architecture that can…

Masked diffusion language models (MDMs) have recently gained traction as a viable generative framework for natural language. This can be attributed to its scalability and ease of training compared to other diffusion model paradigms for…

Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of…

The impressive capacity shown by recent text-to-image diffusion models to generate high-quality pictures from textual input prompts has leveraged the debate about the very definition of art. Nonetheless, these models have been trained using…

Recent advances in large-scale code generation models have led to remarkable progress in producing high-quality code. These models are trained in a self-supervised manner on extensive unlabeled code corpora using a decoder-only…

Under strictly controlled pre-training settings, we observe a Crossover: when unique data is limited, diffusion language models (DLMs) consistently surpass autoregressive (AR) models by training for more epochs. The crossover shifts later…