AromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models

TL;DR

AromaGen is an AI-powered wearable device that generates real-time, customizable aromas from text or images, enabling interactive olfactory experiences and surpassing human-made mixtures after refinement.

Contribution

The paper introduces AromaGen, a novel multimodal language model-based system for real-time, interactive aroma generation from multimodal inputs, addressing dataset scarcity and fixed scent limitations.

Findings

AromaGen matches human-made aroma mixtures in zero-shot generation.

Iterative refinement improves aroma similarity to real food scents.

Perceived artificiality of generated aromas is comparable to real food.

Abstract

Smell's deep connection with food, memory, and social experience has long motivated researchers to bring olfaction into interactive systems. Yet most olfactory interfaces remain limited to fixed scent cartridges and pre-defined generation patterns, and the scarcity of large-scale olfactory datasets has further constrained AI-based approaches. We present AromaGen, an AI-powered wearable interface capable of real-time, general-purpose aroma generation from free-form text or visual inputs. AromaGen is powered by a multimodal LLM that leverages latent olfactory knowledge to map semantic inputs to structured mixtures of 12 carefully selected base odorants, released through a neck-worn dispenser. Users can iteratively refine generated aromas through natural language feedback via in-context learning. Through a controlled user study ($N = 26$), AromaGen matches human-composed mixtures in zero-shot generation and significantly surpasses them after iterative refinement, achieving a median similarity of 8/10 to real food aromas and reducing perceived artificiality to levels comparable to real food. AromaGen is a step towards real-world interactive aroma generation, opening new possibilities for communication, wellbeing, and immersive technologies.