89 citations · 144 across the 22 of their papers we have counts for
23 papers
Debiasing Online Preference Learning via Preference Feature Preservation
Dongyoung Kim, Jinsung Yoon, Jinwoo Shin +1
Recent preference learning frameworks for large language models (LLMs) simplify human preferences with binary pairwise comparisons and scalar rewards. This simplification could mak…
Efficient LLM Collaboration via Planning
Byeongchan Lee, Jonghoon Lee, Dongyoung Kim +4
Recently, large language models (LLMs) have demonstrated strong performance, ranging from simple to complex tasks. However, while large models achieve remarkable results across div…
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Dongyoung Kim, Sumin Park, Huiwon Jang +3
Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training…
Personalized Language Models via Privacy-Preserving Evolutionary Model Merging
Kyuyoung Kim, Jinwoo Shin, Jaehyung Kim
Personalization in language models aims to tailor model behavior to individual users or user groups. Prompt-based methods incorporate user preferences into queries, while training-…
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim +2
Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs)…
Tabular Transfer Learning via Prompting LLMs
Jaehyun Nam, Woomin Song, Seong Hyeon Park +5
Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the…
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
Jaehyun Nam, Kyuyoung Kim, Seunghyuk Oh +3
In tabular prediction tasks, tree-based models combined with automated feature engineering methods often outperform deep learning approaches that rely on learned representations. W…
Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
Dongyoung Kim, Kimin Lee, Jinwoo Shin +1
Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human…
SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
Jaehyung Kim, Jaehyun Nam, Sangwoo Mo +5
Large language models (LLMs) have made significant advancements in various natural language processing tasks, including question answering (QA) tasks. While incorporating new infor…
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
Woomin Song, Seunghyuk Oh, Sangwoo Mo +4
Large language models (LLMs) have shown remarkable performance in various natural language processing tasks. However, a primary constraint they face is the context limit, i.e., the…
Online Adaptation of Language Models with a Memory of Amortized Contexts
Jihoon Tack, Jaehyung Kim, Eric Mitchell +3
Due to the rapid generation and dissemination of information, large language models (LLMs) quickly run out of date despite enormous development costs. To address the crucial need t…
infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information
Jaehyung Kim, Yekyung Kim, Karin de Langis +2
The success of NLP systems often relies on the availability of large, high-quality datasets. However, not all samples in these datasets are equally valuable for learning, as some m…
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning
Jaehyung Kim, Jinwoo Shin, Dongyeop Kang
The development of largely human-annotated benchmarks has driven the success of deep neural networks in various NLP tasks. To enhance the effectiveness of existing benchmarks, coll…
Annotation Imputation to Individualize Predictions: Initial Studies on Distribution Dynamics and Model Predictions
London Lowmanstone, Ruyuan Wan, Risako Owan +2
Annotating data via crowdsourcing is time-consuming and expensive. Due to these costs, dataset creators often have each annotator label only a small subset of the data. This leads…
Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information
Ruyuan Wan, Jaehyung Kim, Dongyeop Kang
In NLP annotation, it is common to have multiple annotators label the text and then obtain the ground truth labels based on the agreement of major annotators. However, annotators a…
Time Is MattEr: Temporal Self-supervision for Video Transformers
Sukmin Yun, Jaehyung Kim, Dongyoon Han +3
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively ex…
Patch-level Representation Learning for Self-supervised Vision Transformers
Sukmin Yun, Hankook Lee, Jaehyung Kim +1
Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance f…
Controllable Missingness from Uncontrollable Missingness: Joint Learning Measurement Policy and Imputation
Seongwook Yoon, Jaehyun Kim, Heejeong Lim +1
Due to the cost or interference of measurement, we need to control measurement system. Assuming that each variable can be measured sequentially, there exists optimal policy choosin…
Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation
Junhyun Nam, Jaehyung Kim, Jaeho Lee +1
The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes. T…
Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy space in Autonomous Driving
Jaehyun Kim, Jaeseung Jeong
Despite advances in hierarchical reinforcement learning, its applications to path planning in autonomous driving on highways are challenging. One reason is that conventional hierar…
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
Jaehyung Kim, Youngbum Hur, Sejun Park +3
While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that t…
M2m: Imbalanced Classification via Major-to-minor Translation
Jaehyung Kim, Jongheon Jeong, Jinwoo Shin
In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this pa…
Simplified Stochastic Feedforward Neural Networks
Kimin Lee, Jaehyung Kim, Song Chong +1
It has been believed that stochastic feedforward neural networks (SFNNs) have several advantages beyond deterministic deep neural networks (DNNs): they have more expressive power a…