Teaching Machines to Smell: New York Smells Dataset

Kari Jaaskelainen

26 Nov 2025 — 1 min read

What if computers could not only see, but also smell? Researchers introduce New York Smells, a large, real-world dataset pairing photos with olfactory sensor readings.

The set spans 7,000 smell-image pairs from 3,500 different objects across indoor and outdoor environments—about 70x more objects than prior smell datasets. That scale opens the door to training AI that understands the world through scent.

Match a smell to the right photo (cross-modal retrieval)
Recognize scenes, objects, and materials from smell alone
Tell apart closely related scents—like different grass species

Early results: visual data helps machines learn richer scent representations, and these learned features beat widely used hand-crafted ones.

Smell is a core sense for animals. This work brings it closer to machines.

Dive into the paper: https://arxiv.org/abs/2511.20544v1

Paper: https://arxiv.org/abs/2511.20544v1

Register: https://www.AiFeta.com

#AI #MachineLearning #ComputerVision #Robotics #Olfaction #Multimodal #Datasets #Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A