Understanding the Quality-Diversity Trade-off in Diffusion Language Models
Diffusion models have seen immense success in modelling continuous data across a range of domains such as vision and audio. Despite the challenges of adapting diffusion models to discrete data, recent work explores their application to text generation by working in the continuous embedding space. However, these models lack a natural means to control the inherent trade-off between quality and diversity as afforded by the temperature hyperparameter in autoregressive models, hindering understanding of model performance and restricting generation quality. This work proposes the use of classifier-free guidance and stochastic clamping for manipulating the quality-diversity trade-off on sequence-to-sequence tasks, demonstrating that these techniques may be used to improve the performance of a diffusion language model.
Code (1)
Tasks
DiversityLanguage ModelingLanguage ModellingText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models
We introduce DiverseVAR, a framework that enhances the diversity of text-conditioned visual autoregressive models (VAR) at test time without requiring retraining, fine-tuning, or substantial computational overhead. While…
Image GenerationBIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving
Large language model (LLM) serving creates environmental impacts beyond carbon and water, including ecosystem damage through biodiversity-related pathways. We present BIRDS, a framework for Biodiversity Impact of Request…
Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models
Text-to-image (T2I) diffusion models have become prominent tools for generating high-fidelity images from text prompts. However, when trained on unfiltered internet data, these models can produce unsafe, incorrect, or st…
DiversityText-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression
We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sticker image generation as the target doma…
DiversityImage GenerationPrompt EngineeringSwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher
In this paper, we aim to enhance the performance of SwiftBrush, a prominent one-step text-to-image diffusion model, to be competitive with its multi-step Stable Diffusion counterpart. Initially, we explore the quality-di…
Diversity