5 citations · 12 across the 19 of their papers we have counts for
20 papers
From Drift to Coherence: Stabilizing Beliefs in LLMs
SongEun Kim, Seungyoo Lee, Edwin Fong +2
Large language models (LLMs) are often hypothesized to perform implicit Bayesian inference, yet a key coherence condition, the martingale property of predictive beliefs, has been s…
Parallel Test-Time Scaling with Multi-Sequence Verifiers
Yegon Kim, Seungyoo Lee, Chaeyun Jang +2
Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it i…
Compact Memory for Continual Logistic Regression
Yohan Jung, Hyungi Lee, Wenlong Chen +4
Despite recent progress, continual learning still does not match the performance of batch training. To avoid catastrophic forgetting, we need to build compact memory of essential p…
Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision
Chaeyun Jang, Moonseok Choi, Yegon Kim +2
Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has…
Variational Bayesian Pseudo-Coreset
Hyungi Lee, Seungyoo Lee, Juho Lee
The success of deep learning requires large datasets and extensive training, which can create significant computational challenges. To address these challenges, pseudo-coresets, sm…
Dimension Agnostic Neural Processes
Hyungi Lee, Chaeyun Jang, Dongbok Lee +1
Meta-learning aims to train models that can generalize to new tasks with limited labeled data by extracting shared features across diverse task datasets. Additionally, it accounts…
Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
Chaeyun Jang, Hyungi Lee, Jungtaek Kim +1
Fine-tuning pre-trained models for downstream tasks is a widely adopted technique known for its adaptability and reliability across various domains. Despite its conceptual simplici…
Enhancement of text recognition for hanja handwritten documents of Ancient Korea
Joonmo Ahna, Taehong Jang, Quan Fengnyu +3
We implemented a high-performance optical character recognition model for classical handwritten documents using data augmentation with highly variable cropping within the document…
Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation
Chaeyun Jang, Deukhwan Cho, Seanie Lee +2
Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confi…
Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
Byoungwoo Park, Hyungi Lee, Juho Lee
Many real-world datasets, such as healthcare, climate, and economics, are often collected as irregular time series, which poses challenges for accurate modeling. In this paper, we…
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…
Joint-Embedding Masked Autoencoder for Self-supervised Learning of Dynamic Functional Connectivity from the Human Brain
Jungwon Choi, Hyungi Lee, Byung-Hoon Kim +1
Graph Neural Networks (GNNs) have shown promise in learning dynamic functional connectivity for distinguishing phenotypes from human brain networks. However, obtaining extensive la…
Function Space Bayesian Pseudocoreset for Bayesian Neural Networks
Balhae Kim, Hyungi Lee, Juho Lee
A Bayesian pseudocoreset is a compact synthetic dataset summarizing essential information of a large-scale dataset and thus can be used as a proxy dataset for scalable Bayesian inf…
Transfer Learning across Several Centuries: Machine and Historian Integrated Method to Decipher Royal Secretary's Diary
Sojung Lucia Kim, Taehong Jang, Joonmo Ahn +2
A named entity recognition and classification plays the first and foremost important role in capturing semantics in data and anchoring in translation as well as downstream study fo…
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…
Regularizing Towards Soft Equivariance Under Mixed Symmetries
Hyunsu Kim, Hyungi Lee, Hongseok Yang +1
Datasets often have their intrinsic symmetries, and particular deep-learning models called equivariant or invariant models have been developed to exploit these symmetries. However,…
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…
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…
Scale Mixtures of Neural Network Gaussian Processes
Hyungi Lee, Eunggu Yun, Hongseok Yang +1
Recent works have revealed that infinitely-wide feed-forward or recurrent neural networks of any architecture correspond to Gaussian processes referred to as Neural Network Gaussia…