Related papers: ELF: Embedded Language Flows
Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…
This survey paper provides a comprehensive review of the use of diffusion models in natural language processing (NLP). Diffusion models are a class of mathematical models that aim to capture the diffusion of information or signals across a…
Recent advancements in Language Models (LMs) have demonstrated strong semantic reasoning capabilities, enabling their application in high-level decision-making for autonomous driving (AD). However, LMs operate over discrete token spaces and…
Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding capabilities of LLMs, most existing LLM-based rerankers rely…
Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices. Rather than using typical natural language processing (NLP) approaches, recent research…
Diffusion models offer appealing properties for language generation, such as parallel decoding and iterative refinement, but the discrete and highly structured nature of text challenges the direct application of diffusion principles. In…
Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…
Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…
Recent advances in distilling expensive diffusion models into efficient few-step generators show significant promise. However, these methods typically demand substantial computational resources and extended training periods, limiting…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…
Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from…
Diffusion LLMs have been proposed as an alternative to autoregressive LLMs, excelling especially at complex reasoning tasks with interdependent sub-goals. Curiously, this is particularly true if the generation length, i.e., the number of…
Recently, the application of diffusion probabilistic models has advanced speech enhancement through generative approaches. However, existing diffusion-based methods have focused on the generation process in high-dimensional waveform or…
Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks. While it has previously demonstrated remarkable improvements for the sample quality, it has only been…
Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price…
Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this…
Diffusion probabilistic models have quickly become a major approach for generative modeling of images, 3D geometry, video and other domains. However, to adapt diffusion generative modeling to these domains the denoising network needs to be…
Text embedding has become a foundational technology in natural language processing (NLP) during the deep learning era, driving advancements across a wide array of downstream tasks. While many natural language understanding challenges can…
We develop a diffusion-based approach for various document layout sequence generation. Layout sequences specify the contents of a document design in an explicit format. Our novel diffusion-based approach works in the sequence domain rather…
The presence of missing values within high-dimensional data is an ubiquitous problem for many applied sciences. A serious limitation of many available data mining and machine learning methods is their inability to handle partially missing…