arXiv：cs.AI· Awu Chen, Silang Wang, Yunge Wen, Jianing Yu, Zinab Eisa, Ana Julia Santos Lopes, Jas Brooks, Hiroshi Ishii, Paul Pu Liang·· 5 小时前
AromaGen：用多模态语言模型交互生成丰富嗅觉体验
AromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models
AI 导读
AromaGen 是一套 AI 驱动的 12 通道可穿戴嗅觉系统，可将自由文本描述映射到 12 种基础气味分子，并支持通过自然语言反馈迭代调整。在 N=60 的受试者间研究中，涵盖 50 种真实基准气味，参与者能在三选一强制选择任务中以高于随机的水平辨认出 AromaGen 生成的目标气味，其中检索增强的 AI 配方与人类专家配方、零样本 AI 配方表现相当。
正文
Abstract:Smell's connections with food, memory, and social experience have motivated researchers to bring olfaction into interactive systems. Multimodal AI opens new possibilities for generating smells from natural language, yet it remains unclear whether pretrained models encode sufficient olfactory knowledge to translate language into perceptible compositions. We present AromaGen, an AI-powered 12-channel wearable olfactory system that maps free-form natural-language descriptions to 12 base odorants selected to cover a semantically derived olfactory space, while supporting iterative refinement through natural-language feedback. In a between-subjects study (N=60) across 50 real-world benchmark smells, participants distinguished AromaGen-generated target smells above chance in a three-alternative forced-choice task, with retrieval-augmented AI composition performing comparably to human-expert composition and zero-shot AI composition. Natural-language feedback significantly improved the perceived similarity of both AI- and human-expert compositions. Our findings demonstrate the feasibility of using pretrained multimodal AI, with human aroma composition data, to generate perceptible olfactory experiences from natural language.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2604.01650 [cs.HC] |
| (or arXiv:2604.01650v4 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2604.01650 arXiv-issued DOI via DataCite |
Submission history
From: Awu Chen [view email]
[v1]
Thu, 2 Apr 2026 05:47:07 UTC (6,228 KB)
[v2]
Thu, 23 Apr 2026 23:14:51 UTC (6,228 KB)
[v3]
Sat, 26 Sep 2026 04:00:39 UTC (10,783 KB)
[v4]
Fri, 9 Oct 2026 21:06:06 UTC (10,784 KB)
来源：arXiv：cs.AI · arxiv.org