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

• URL: http://arxiv.org/abs/2604.01650v1
• Date: Thu, 02 Apr 2026 05:47:07 GMT
• Title: AromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models
• Abstract summary: AromaGen is an AI-powered wearable interface capable of real-time, general-purpose aroma generation from free-form text or visual inputs.<n> AromaGen matches human-composed mixtures in zero-shot generation and significantly surpasses them after iterative refinement.
• Score: 29.111586871914167
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• See & Sniff: Learning Visuo-Olfactory Representations [42.26043073031702]
  We introduce SmellNet-V, a scalable visuo-olfactory dataset built on the insight that odor identity is largely invariant to visual transformations within a semantic category.<n>This allows us to synthetically pair smell-only samples with semantically aligned in-the-wild web images, converting a unimodal olfactory dataset into a cross-modal benchmark.<n>We propose See & Sniff, a self-supervised framework that learns joint visuo-olfactory representations via dense local alignment.
  arXiv  Detail & Related papers  (2026-06-25T17:26:47Z)
• New York Smells: A Large Multimodal Dataset for Olfaction [93.162210916881]
  We present New York Smells, a large dataset of paired image and olfactory signals captured in the wild''<n>Our dataset contains 7,000 smell-image pairs from 3,500 distinct objects across indoor and outdoor environments.<n>Our benchmark has three tasks: cross-modal smell-to-image retrieval, recognizing scenes, objects, and materials from smell alone, and fine-grained discrimination between grass species.
  arXiv  Detail & Related papers  (2025-11-25T17:44:50Z)
• Diffusion Graph Neural Networks and Dataset for Robust Olfactory Navigation in Hazard Robotics [0.0]
  Navigation by scent is a capability in robotic systems that is rising in demand.<n>Current methods often suffer from ambiguities, particularly when robots misattribute odours to incorrect objects.<n>We introduce a multimodal olfaction dataset along with a novel machine learning method.
  arXiv  Detail & Related papers  (2025-05-31T08:22:09Z)
• WeGen: A Unified Model for Interactive Multimodal Generation as We Chat [51.78489661490396]
  We introduce WeGen, a model that unifies multimodal generation and understanding.<n>It can generate diverse results with high creativity for less detailed instructions.<n>We show it achieves state-of-the-art performance across various visual generation benchmarks.
  arXiv  Detail & Related papers  (2025-03-03T02:50:07Z)
• Navigating the Fragrance space Via Graph Generative Models And Predicting Odors [0.2749898166276853]
  We explore a suite of generative modelling techniques to efficiently navigate and explore the complex landscapes of odor and the broader chemical space.<n>Unlike traditional approaches, we not only generate molecules but also predict the odor likeliness with ROC AUC score of 0.97 and assign probable odor labels.
  arXiv  Detail & Related papers  (2025-01-30T22:00:23Z)
• Molecule Generation and Optimization for Efficient Fragrance Creation [0.0]
  This research introduces a Machine Learning-centric approach to replicate olfactory experiences. Key contributions encompass a hybrid model connecting perfume molecular structure to human olfactory perception. The methodology is validated by reproducing two distinct olfactory experiences using available experimental data.
  arXiv  Detail & Related papers  (2024-02-19T13:32:30Z)
• Olfactory Label Prediction on Aroma-Chemical Pairs [0.2749898166276853]
  We present graph neural network models capable of accurately predicting the odor qualities arising from blends of aroma-chemicals. In this paper, we apply both existing and novel approaches to a dataset we gathered consisting of labeled pairs of molecules.
  arXiv  Detail & Related papers  (2023-12-26T17:18:09Z)
• Diffusion Recommender Model [85.9640416600725]
  We propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner.<n>To retain personalized information in user interactions, DiffRec reduces the added noises and avoids corrupting users' interactions into pure noises like in image synthesis.
  arXiv  Detail & Related papers  (2023-04-11T04:31:00Z)
• Detecting Human-Object Interaction via Fabricated Compositional Learning [106.37536031160282]
  Human-Object Interaction (HOI) detection is a fundamental task for high-level scene understanding. Human has extremely powerful compositional perception ability to cognize rare or unseen HOI samples. We propose Fabricated Compositional Learning (FCL) to address the problem of open long-tailed HOI detection.
  arXiv  Detail & Related papers  (2021-03-15T08:52:56Z)
• Multilinear Latent Conditioning for Generating Unseen Attribute Combinations [61.686839319971334]
  We show that variational autoencoders (VAE) and generative adversarial networks (GAN) lack the generalization ability that occurs naturally in human perception. We introduce a multilinear latent conditioning framework that captures the multiplicative interactions between attributes. Altogether, we design a novel conditioning framework that can be used with any architecture to synthesize unseen attribute combinations.
  arXiv  Detail & Related papers  (2020-09-09T02:23:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.