PulseAugur
LIVE 14:50:39
research · [1 source] ·
0
research

AromaGen uses multimodal LLMs to generate aromas from text and images

Researchers have developed AromaGen, a wearable device that uses a multimodal language model to generate aromas from text or visual inputs. The system maps semantic inputs to mixtures of 12 base odorants, allowing for real-time, interactive scent creation. In user studies, AromaGen demonstrated significant accuracy in matching real food aromas and reducing perceived artificiality, marking a step towards interactive aroma generation for various applications. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enables new forms of sensory interaction and immersive experiences through AI-driven scent generation.

RANK_REASON Academic paper detailing a novel AI-powered system for aroma generation.

Read on arXiv cs.AI →

COVERAGE [1]

  1. arXiv cs.AI TIER_1 · Yunge Wen, Awu Chen, Jianing Yu, Jas Brooks, Hiroshi Ishii, Paul Pu Liang ·

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

    arXiv:2604.01650v2 Announce Type: replace-cross 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-de…