Related papers: ShortListing Model: A Streamlined SimplexDiffusion…
Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…
This document presents some early explorations of applying Softly Masked Language Modelling (SMLM) to symbolic music generation. SMLM can be seen as a generalisation of masked language modelling (MLM), where instead of each element of the…
Although large vision-language models (LVLMs) have demonstrated impressive capabilities in multi-modal understanding and reasoning, their practical applications are still limited by massive model parameters and high computational costs.…
Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods…
Conditional graphic layout generation, which automatically maps user constraints to high-quality layouts, has attracted widespread attention today. Although recent works have achieved promising performance, the lack of versatility and data…
Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. In particular, their ability to generate reasoning traces motivated their use in many prediction tasks like math…
To model discrete sequences such as DNA, proteins, and language using diffusion, practitioners must choose between three major methods: diffusion in discrete space, Gaussian diffusion in Euclidean space, or diffusion on the simplex. Despite…
Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity and memory demands, complicating deployment, raising…
Extractive summarization aims to form a summary by directly extracting sentences from the source document. Existing works mostly formulate it as a sequence labeling problem by making individual sentence label predictions. This paper…
This work studies discrete diffusion probabilistic models with applications to natural language generation. We derive an alternative yet equivalent formulation of the sampling from discrete diffusion processes and leverage this insight to…
Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks. Despite the success of these models, their high…
Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…
Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribution. While…
Large Language Models (LLMs) have demonstrated impressive quality when applied to predictive tasks such as relevance ranking and semantic search. However, deployment of such LLMs remains prohibitively expensive for industry applications…
Diffusion Large Language Models (DLLMs) are inherently ill-suited for variable-length generation, as their inference is defined on a fixed-length canvas and implicitly assumes a known target length. When the length is unknown, as in…
Generative Spoken Language Modeling research focuses on optimizing speech Language Models (LMs) using raw audio recordings without accessing any textual supervision. Such speech LMs usually operate over discrete units obtained from…
The modern autoregressive Large Language Models (LLMs) have achieved outstanding performance on NLP benchmarks, and they are deployed in the real world. However, they still suffer from limitations of the autoregressive training paradigm.…
We provide theoretical convergence guarantees for score-based generative models (SGMs) such as denoising diffusion probabilistic models (DDPMs), which constitute the backbone of large-scale real-world generative models such as DALL$\cdot$E…
Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.g., molecular generation, robotics). We present a unified framework for…
Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive…