Related papers: Can Transformers Smell Like Humans?

Humans and animals excel in combining information from multiple sensory modalities, controlling their complex bodies, adapting to growth, failures, or using tools. These capabilities are also highly desirable in robots. They are displayed…

Embeddings from contemporary natural language processing (NLP) models are commonly used as numerical representations for words or sentences. However, odor descriptor words, like "leather" or "fruity", vary significantly between their…

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to understand the role of…

In recent years, the transformer architecture has become the de facto standard for machine learning algorithms applied to natural language processing and computer vision. Despite notable evidence of successful deployment of this…

Large language models encode knowledge in various domains and demonstrate the ability to understand visualizations. They may also capture visualization design knowledge and potentially help reduce the cost of formative studies. However, it…

Transformers have excelled in natural language processing and computer vision, paving their way to sensor-based Human Activity Recognition (HAR). Previous studies show that transformers outperform their counterparts exclusively when they…

The mammalian olfactory system learns rapidly from very few examples, presented in unpredictable online sequences, and then recognizes these learned odors under conditions of substantial interference without exhibiting catastrophic…

Despite being designed for performance rather than cognitive plausibility, transformer language models have been found to be better at predicting metrics used to assess human language comprehension than language models with other…

Machine olfaction is rapidly emerging as a transformative capability, with applications spanning non-invasive medical diagnostics, industrial monitoring, agriculture, and security and defense. Recent advances in stabilizing mammalian…

Neural methods of molecule property prediction require efficient encoding of structure and property relationship to be accurate. Recent work using graph algorithms shows limited generalization in the latent molecule encoding space. We build…

In drug-discovery-related tasks such as virtual screening, machine learning is emerging as a promising way to predict molecular properties. Conventionally, molecular fingerprints (numerical representations of molecules) are calculated…

Odor sensory evaluation has a broad application in food, clothing, cosmetics, and other fields. Traditional artificial sensory evaluation has poor repeatability, and the machine olfaction represented by the electronic nose (E-nose) is…

We present a model of an olfactory system that performs odor segmentation. Based on the anatomy and physiology of natural olfactory systems, it consists of a pair of coupled modules, bulb and cortex. The bulb encodes the odor inputs as…

Deep transformer models have pushed performance on NLP tasks to new limits, suggesting sophisticated treatment of complex linguistic inputs, such as phrases. However, we have limited understanding of how these models handle representation…

Transformers have made significant strides across various artificial intelligence domains, including natural language processing, computer vision, and audio processing. This success has naturally garnered considerable interest from both…

Many of today's robot perception systems aim at accomplishing perception tasks that are too simplistic and too hard. They are too simplistic because they do not require the perception systems to provide all the information needed to…

Our sense of smell relies on sensitive, selective atomic-scale processes that are initiated when a scent molecule meets specific receptors in the nose. However, the physical mechanisms of detection are not clear. While odorant shape and…

Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…

This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independently, the PET model's decoder embedding incorporates shared…

One of the key challenges to predict odor from molecular structure is unarguably our limited understanding of the odor space and the complexity of the underlying structure-odor relationships. Here, we show that the predictive performance of…