8 citations · 11 across the 6 of their papers we have counts for
6 papers
Few-Shot LoRA Adaptation of a Flow-Matching Foundation Model for Cross-Spectral Object Detection
Maxim Clouser, Kia Khezeli, John Kalantari
Foundation models for vision are predominantly trained on RGB data, while many safety-critical applications rely on non-visible modalities such as infrared (IR) and synthetic apert…
CausalARC: Abstract Reasoning with Causal World Models
Jacqueline Maasch, John Kalantari, Kia Khezeli
On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning…
Beyond Low Earth Orbit: Biomonitoring, Artificial Intelligence, and Precision Space Health
Ryan T. Scott, Erik L. Antonsen, Lauren M. Sanders +53
Human space exploration beyond low Earth orbit will involve missions of significant distance and duration. To effectively mitigate myriad space health hazards, paradigm shifts in d…
Invariant Risk Minimisation for Cross-Organism Inference: Substituting Mouse Data for Human Data in Human Risk Factor Discovery
Odhran O'Donoghue, Paul Duckworth, Giuseppe Ughi +10
Human medical data can be challenging to obtain due to data privacy concerns, difficulties conducting certain types of experiments, or prohibitive associated costs. In many setting…
Universally Rank Consistent Ordinal Regression in Neural Networks
Garrett Jenkinson, Gavin R. Oliver, Kia Khezeli +2
Despite the pervasiveness of ordinal labels in supervised learning, it remains common practice in deep learning to treat such problems as categorical classification using the categ…
On Invariance Penalties for Risk Minimization
Kia Khezeli, Arno Blaas, Frank Soboczenski +2
The Invariant Risk Minimization (IRM) principle was first proposed by Arjovsky et al. [2019] to address the domain generalization problem by leveraging data heterogeneity from diff…