Papers
arxiv:2505.18853

Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation

Published on May 24
Authors:
,
,

Abstract

Smoothie, a novel diffusion method, improves text generation quality by smoothing token embeddings based on semantic similarity, outperforming existing diffusion-based models.

AI-generated summary

Diffusion models have achieved state-of-the-art performance in generating images, audio, and video, but their adaptation to text remains challenging due to its discrete nature. Prior approaches either apply Gaussian diffusion in continuous latent spaces, which inherits semantic structure but struggles with token decoding, or operate in categorical simplex space, which respect discreteness but disregard semantic relation between tokens. In this paper, we propose Smoothing Diffusion on Token Embeddings (Smoothie), a novel diffusion method that combines the strengths of both approaches by progressively smoothing token embeddings based on semantic similarity. This technique enables gradual information removal while maintaining a natural decoding process. Experimental results on several sequence-to-sequence generation tasks demonstrate that Smoothie outperforms existing diffusion-based models in generation quality. Furthermore, ablation studies show that our proposed diffusion space yields better performance than both the standard embedding space and the categorical simplex. Our code is available at https://github.com/ashaba1in/smoothie.

Community

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2505.18853 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2505.18853 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.