3 papers
cs.LG2025
Improving Constrained Language Generation via Self-Distilled Twisted Sequential Monte Carlo
Sooyeon Kim, Giung Nam, Byoungwoo Park +1
Recent work has framed constrained text generation with autoregressive language models as a probabilistic inference problem. Among these, Zhao et al. (2024) introduced a promising…
cs.LG2025
Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo
Hyunsu Kim, Giung Nam, Chulhee Yun +2
Bayesian Neural Networks (BNNs) provide a promising framework for modeling predictive uncertainty and enhancing out-of-distribution robustness (OOD) by estimating the posterior dis…
cs.LG2024
Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
Giung Nam, Juho Lee
While ensembling deep neural networks has shown promise in improving generalization performance, scaling current ensemble methods for large models remains challenging. Given that r…