collaborators

21 papers

stat.ME2026

AdaptICA: Data-Adaptive Transformation Learning for Independent Component Analysis

Lida Jalili, Jingyu Liu, Vince D. Calhoun +1

Independent component analysis (ICA) is widely used to recover latent structure from signal and imaging data, but standard ICA assumes that the observed measurement scale preserves…

cs.LG2026

Latent graph encoding of multimodal neuroimaging features with generative AI architectures

Ishaan Batta, Meenu Ajith, Vince Calhoun

While generative models enable encoding of complex neuroimaging data for feature generation and reconstruction, developing optimal architectural frameworks with appropriate encodin…

cs.CV2026

ReMAP-PET: Beyond Visual Understanding -- Learning Region-Guided Metabolic Alignment Semantics from Brain PET

Dasen Dai, Yanteng Zhang, Shuoqi Li +6

Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain foundation models treat PET as…

stat.ML2026

Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability

Yi-Ting Hung, Li-Hsiang Lin, Vince D. Calhoun

Recent advances in deep learning highlight the need for personalized models that can learn from small samples, handle high-dimensional features, and remain interpretable. To addres…

cond-mat.stat-mech2026

Timescale Coalescence Makes Hidden Persistent Forcing Spectrally Dark

Yuda Bi, Chenyu Zhang, Vince D Calhoun

Under coarse observation, unresolved slow forcing can remain dynamically active yet locally invisible to reduced spectral inference. For a solvable driven AR benchmark, the lo…

cs.LG2026

Scaling Laws are Redundancy Laws

Yuda Bi, Vince D Calhoun

Scaling laws, a defining feature of deep learning, reveal a striking power-law improvement in model performance with increasing dataset and model size. Yet, their mathematical orig…