Researchers Develop AI Device Synthesizing Personalized Scents
Researchers at MIT Media Lab and Harvard University have developed the Anemoia Device, a tactile olfactory system that analyzes printed photographs with vision-language models and uses LLMs to generate short narratives tied to image subjects. It maps narratives to an olfactory vector that selects up to four scents from a 39-preblended-oil library and dispenses milliliter-accurate blends via four peristaltic pumps controlled by a Seeed Studio XIAO ESP32S3 microcontroller, aiming to evoke synthetic nostalgia and enrich memory engagement.
Key Points
- 1Convert photos into narratives and olfactory vectors using vision-language models and LLMs
- 2Map narratives to scents selecting up to four oils from a 39-fragrance library
- 3Enable researchers and designers to prototype multisensory memory experiences and study olfactory-augmented interactions
Scoring Rationale
Novel multisensory research with solid institutional credibility, but limited immediate industry impact and niche practical applicability.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
