34 citations · 56 across the 67 of their papers we have counts for
33 papers · 1 filter
Dynamic Expert Pruning for Multi-Agent Systems
Jabin Koo, Soheil Abbasloo, Sungjae Lee +1
Mixture-of-Experts (MoE) architectures scale language models efficiently by activating only a few experts per token, but the saving is confined to computation: every expert must st…
AdaBoosting Text Prompts for Vision-Language Models
Seokhee Jin, Changhwan Sung, Sunung Mun +2
The classification accuracy of pretrained Vision-Language Models (VLMs) relies on the quality of the text prompts. Handcrafted templates and Large Language Model (LLM)-generated de…
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
Jabin Koo, Hoyoung Kim, Minwoo Jang +1
Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce a monolithic reward model, ine…
Interaction-Aware Influence Functions for Group Attribution
Jaeseung Heo, Kyeongheung Yun, Youngbin Choi +3
Influence functions approximate how removing a training example changes a quantity of interest, called the target function, such as a held-out loss. To estimate the influence of a…
When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models
Youngsik Yoon, Siwei Wang, Wei Chen +1
Mixture-of-Experts (MoE) language models route each token to a small subset of experts, but whether the routes selected by a trained top- router are good ones is rarely evaluate…
Rising Multi-Armed Bandits with Known Horizons
Seockbean Song, Chenyu Gan, Youngsik Yoon +3
Rising Multi-Armed Bandits (RMABs) model sequential decision problems where each arm's expected reward improves with repeated pulls. In such problems, the value of investing in an…
Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark
Suyeon Kim, SeongKu Kang, Dongwoo Kim +2
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification tasks but struggle with label noise in real-world data. Existing studies on graph lea…
Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
Jaeseung Heo, Kyeongheung Yun, Seokwon Yoon +3
Understanding how individual edges influence the behavior of graph neural networks (GNNs) is essential for improving their interpretability and robustness. Graph influence function…
Self-Training Large Language Models with Confident Reasoning
Hyosoon Jang, Yunhui Jang, Sungjae Lee +2
Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers, but learning such a reasoning path requires costly human supervis…
Experience-based Knowledge Correction for Robust Planning in Minecraft
Seungjoon Lee, Suhwan Kim, Minhyeon Oh +2
Large Language Model (LLM)-based planning has advanced embodied agents in long-horizon environments such as Minecraft, where acquiring latent knowledge of goal (or item) dependenci…
Revisiting Early Detection of Sexual Predators via Turn-level Optimization
Jinmyeong An, Sangwon Ryu, Heejin Do +3
Online grooming is a severe social threat where sexual predators gradually entrap child victims with subtle and gradual manipulation. Therefore, timely intervention for online groo…
CoPL: Collaborative Preference Learning for Personalizing LLMs
Youngbin Choi, Seunghyuk Cho, Minjong Lee +4
Personalizing large language models (LLMs) is important for aligning outputs with diverse user preferences, yet existing methods struggle with flexibility and generalization. We pr…
Enhancing Cost Efficiency in Active Learning with Candidate Set Query
Yeho Gwon, Sehyun Hwang, Hoyoung Kim +2
This paper introduces a cost-efficient active learning (AL) framework for classification, featuring a novel query design called candidate set query. Unlike traditional AL queries r…
Combinatorial Rising Bandits
Seockbean Song, Youngsik Yoon, Siwei Wang +2
Combinatorial online learning is a fundamental task for selecting the optimal action (or super arm) as a combination of base arms in sequential interactions with systems providing…
Comparison-based Active Preference Learning for Multi-dimensional Personalization
Minhyeon Oh, Seungjoon Lee, Jungseul Ok
Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge. As individuals have their own, multi-dimensional pref…
Retrieval-Augmented Generation with Estimation of Source Reliability
Jeongyeon Hwang, Junyoung Park, Hyejin Park +3
Retrieval-Augmented Generation (RAG) is an effective approach to enhance the factual accuracy of large language models (LLMs) by retrieving information from external databases, whi…
Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients
Jabin Koo, Minwoo Jang, Jungseul Ok
Federated fine-tuning for Large Language Models (LLMs) faces significant challenges due to the heavy communication overhead of transmitting large model updates. Although Low Rank A…
Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation
Jaechang Kim, Jinmin Goh, Inseok Hwang +2
Deep learning-based expert models have reached superhuman performance in decision-making domains such as chess and Go. However, it is under-explored to explain or comment on given…
Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization
Nayeong Kim, Juwon Kang, Sungsoo Ahn +2
We study the problem of training an unbiased and accurate model given a dataset with multiple biases. This problem is challenging since the multiple biases cause multiple undesirab…
MedBN: Robust Test-Time Adaptation against Malicious Test Samples
Hyejin Park, Jeongyeon Hwang, Sunung Mun +2
Test-time adaptation (TTA) has emerged as a promising solution to address performance decay due to unforeseen distribution shifts between training and test data. While recent TTA m…
Combating Label Distribution Shift for Active Domain Adaptation
Sehyun Hwang, Sohyun Lee, Sungyeon Kim +2
We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent a…
Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning
Byungchan Ko, Jungseul Ok
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and…
MetaSSD: Meta-Learned Self-Supervised Detection
Moon Jeong Park, Jungseul Ok, Yo-Seb Jeon +1
Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervis…
Few-Shot Unlearning by Model Inversion
Youngsik Yoon, Jinhwan Nam, Hyojeong Yun +3
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model. The target dataset is often assumed to be…