activity
20242026
most citedSmell with Genji: Rediscovering Human Perception through an Olfactory Game with AI

1 citations · 1 across the 3 of their papers we have counts for

collaborators

6 papers

cs.HC20261 cited

Smell with Genji: Rediscovering Human Perception through an Olfactory Game with AI

Awu Chen, Vera Yu Wu, Yunge Wen +7

Olfaction plays an important role in human perception, yet its subjective and ephemeral nature makes it difficult to articulate, compare, and share across individuals. Traditional…

cs.LG2026

A Vision for Multisensory Intelligence: Sensing, Science, and Synergy

Paul Pu Liang

Our experience of the world is multisensory, spanning a synthesis of language, sight, sound, touch, taste, and smell. Yet, artificial intelligence has primarily advanced in digital…

cs.AI2025

When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning

Chenyu Zhang, Minsol Kim, Shohreh Ghorbani +4

Despite rapid growth in multimodal large language models (MLLMs), their reasoning traces remain opaque: it is often unclear which modality drives a prediction, how conflicts are re…

cs.ET2025

Machine Olfaction and Embedded AI Are Shaping the New Global Sensing Industry

Andreas Mershin, Nikolas Stefanou, Adan Rotteveel +7

Machine olfaction is rapidly emerging as a transformative capability, with applications spanning non-invasive medical diagnostics, industrial monitoring, agriculture, and security…

cs.LG2025

FAIRWELL: Fair Multimodal Self-Supervised Learning for Wellbeing Prediction

Jiaee Cheong, Abtin Mogharabin, Paul Liang +2

Early efforts on leveraging self-supervised learning (SSL) to improve machine learning (ML) fairness has proven promising. However, such an approach has yet to be explored within a…

cs.LG2024

Balancing Multimodal Training Through Game-Theoretic Regularization

Konstantinos Kontras, Thomas Strypsteen, Christos Chatzichristos +3

Multimodal learning holds promise for richer information extraction by capturing dependencies across data sources. Yet, current training methods often underperform due to modality…