11 papers
Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model
Karla Tame-Narvaez, Aleksandra ÄiprijanoviÄ, Shubhendu Trivedi
Foundation models for astronomical surveys offer powerful learned representations that can be transferred to downstream regression tasks such as galaxy property estimation. However…
On Universality of Deep Equivariant Networks
Marco Pacini, Mircea Petrache, Bruno Lepri +2
Universality results for equivariant neural networks remain rare. Those that do exist typically hold only in restrictive settings: either they rely on regular or higher-order tenso…
Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data
Stefanos Pertigkiozoglou, Mircea Petrache, Shubhendu Trivedi +1
Equivariant neural networks exploit underlying task symmetries to improve generalization, but strict equivariance constraints can induce more complex optimization dynamics that can…
Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
Apurv Verma, NhatHai Phan, Shubhendu Trivedi
Watermarking has become a practical tool for tracing language model outputs, but it modifies token probabilities at inference time, which were carefully tuned by alignment training…
On Universality Classes of Equivariant Networks
Marco Pacini, Gabriele Santin, Bruno Lepri +1
Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separ…
Automating Sensor Characterization with Bayesian Optimization
J. Cuevas-Zepeda, C. Chavez, J. Estrada +6
The development of novel instrumentation requires an iterative cycle with three stages: design, prototyping, and testing. Recent advancements in simulation and nanofabrication tech…