11 citations · 11 across the 11 of their papers we have counts for
5 papers · 1 filter
Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation Models
Sangyoon Bae, Sk Miraj Ahmed, Shinjae Yoo +1
Can we determine whether a foundation model will generalize out-of-distribution (OOD) before any target data is available? Existing diagnostics require source or target data, which…
Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens
Sangyoon Bae, Jiook Cha
Extracellular electrophysiology records a different set of neurons in every session. Neural foundation models embed each neuron and each session into their tokens, so every new ses…
PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift
Sangyoon Bae, Shinjae Yoo, Jiook Cha
Scientific foundation models are expected to reuse representations under changes in dataset, acquisition protocol, and deployment domain, yet many sequence backbones treat scientif…
Latent-Space Causal Discovery from Indirect Neuroimaging Observations
Sangyoon Bae, Miruna Oprescu, David Keetae Park +2
Neuroimaging does not observe causal variables directly: hemodynamics and volume conduction distort signals so that statistical dependence need not reflect latent neural influence.…
Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs
Yujin Jo, Sangyoon Bae, Taesup Kim
Hallucinations in large vision--language models (LVLMs) often arise when language priors dominate over visual evidence, leading to object misidentification and visually inconsisten…