4 papers
A Systematic Evaluation of Sample-Level Tokenization Strategies for MEG Foundation Models
SungJun Cho, Chetan Gohil, Rukuang Huang +2
Recent success in natural language processing has motivated growing interest in large-scale foundation models for neuroimaging data. Such models often require discretization of con…
LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting
Sungjun Cho, Changho Shin, Suenggwan Jo +3
Forecasting in the real world requires integrating structured time-series data with unstructured textual information, but existing methods are architecturally limited by fixed inpu…
Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
Sungjun Cho, Dasol Hwang, Frederic Sala +3
Current unlearning metrics for generative models evaluate success based on reference responses or classifier outputs rather than assessing the core objective: whether the unlearned…
TARDIS: Mitigating Temporal Misalignment via Representation Steering
Changho Shin, Xinya Yan, Suenggwan Jo +3
Language models often struggle with temporal misalignment, performance degradation caused by shifts in the temporal distribution of data. Continuously updating models to avoid degr…