Related papers: Language Modeling with Hyperspherical Flows
In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than 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…
Despite remarkable progress in autoregressive language models, alternative generative paradigms beyond left-to-right generation are still being actively explored. Discrete diffusion models, with the capacity for parallel generation, have…
This paper introduces DiFlow-TTS, a novel zero-shot text-to-speech (TTS) system that employs discrete flow matching for generative speech modeling. We position this work as an entry point that may facilitate further advances in this…
Large language models (LLMs) have shown promising performance across diverse domains. Many practical applications of LLMs, such as code completion and structured data extraction, require adherence to syntactic constraints specified by a…
Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models. Recently, a new paradigm has emerged in the form of diffusion-based Large Language Models (dLLMs), which generate text by iteratively denoising masked…
Learning computational fluid dynamics (CFD) traditionally relies on computationally intensive simulations of the Navier-Stokes equations. Recently, large language models (LLMs) have shown remarkable pattern recognition and reasoning…
Uniform-state discrete diffusion models excel at few-step generation and guidance due to their ability to self-correct, making them preferred over autoregressive or Masked diffusion models in these settings. However, their sampling quality…
We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…
Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong assumptions about the distributions of the target data space. Aiming to improve those assumptions, Normalizing Flows and Diffusion Probabilistic Models…
Denoising diffusion probabilistic models have recently demonstrated state-of-the-art generative performance and have been used as strong pixel-level representation learners. This paper decomposes the interrelation between the generative…
This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs). DLM-One eliminates the need for iterative refinement by aligning the scores of a student…
The rapid advancement of Intelligent Transportation Systems (ITS) presents challenges, particularly with missing data in multi-modal transportation and the complexity of handling diverse sequential tasks within a centralized framework. To…
Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling. In this work, we develop non-asymptotic convergence theory for a…
Diffusion models (DMs) have been adopted across diverse fields with its remarkable abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a stochastic…
Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech…
Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…
We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the curved sampling trajectories of diffusion models into straight-line flows, FlowLM enables…
Masked diffusion models (MDMs) have shown promise in language modeling, yet their scalability and effectiveness in core language tasks, such as text generation and language understanding, remain underexplored. This paper establishes the…
Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…