17 citations · 19 across the 11 of their papers we have counts for
14 papers
Understanding the Mpemba Effect through a Rule of Thumb
Ran Yaacoby
In the Mpemba effect, a system prepared farther from equilibrium relaxes faster than one prepared closer to it. Its persistence across diverse systems, and under different dynamics…
Harness-Aware Distillation for Small Language Model Agents
Moonseok Choi, Taehong Moon, Giung Nam +1
Language model agents are deployed with a harness, the software around the model that manages its context, tools, and feedback. When such an agent is distilled into a smaller one,…
Proper Scoring Rule-based Diffusion for Probabilistic Weather Forecasting
Joonhyeong Park, Giung Nam, Hyungi Lee +3
Recent probabilistic weather forecasters train stochastic predictors with the continuous ranked probability score (CRPS) to generate each ensemble member in a single forward pass.…
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…
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…
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…
Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance
Giung Nam, Byeongho Heo, Juho Lee
Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requir…
Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling
Hyungi Lee, Giung Nam, Edwin Fong +1
Transfer learning has recently shown significant performance across various tasks involving deep neural networks. In these transfer learning scenarios, the prior distribution for d…
Traversing Between Modes in Function Space for Fast Ensembling
EungGu Yun, Hyungi Lee, Giung Nam +1
Deep ensemble is a simple yet powerful way to improve the performance of deep neural networks. Under this motivation, recent works on mode connectivity have shown that parameters o…
Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
Moonseok Choi, Hyungi Lee, Giung Nam +1
Given the ever-increasing size of modern neural networks, the significance of sparse architectures has surged due to their accelerated inference speeds and minimal memory demands.…
Martingale Posterior Neural Processes
Hyungi Lee, Eunggu Yun, Giung Nam +2
A Neural Process (NP) estimates a stochastic process implicitly defined with neural networks given a stream of data, rather than pre-specifying priors already known, such as Gaussi…
Decoupled Training for Long-Tailed Classification With Stochastic Representations
Giung Nam, Sunguk Jang, Juho Lee
Decoupling representation learning and classifier learning has been shown to be effective in classification with long-tailed data. There are two main ingredients in constructing a…
Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation
Giung Nam, Hyungi Lee, Byeongho Heo +1
Ensembles of deep neural networks have demonstrated superior performance, but their heavy computational cost hinders applying them for resource-limited environments. It motivates d…
Diversity Matters When Learning From Ensembles
Giung Nam, Jongmin Yoon, Yoonho Lee +1
Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost…