The Data Intelligence Lab at Korea University is actively seeking undergraduate researchers, Master's and Ph.D. students, and postdoctoral researchers. Interested individuals are encouraged to contact Prof. Lee.

고려대학교 데이터 지능 연구실에서는 학부 연구생, 석·박사 대학원생, 박사후 연구원을 수시 모집한다. 관심 있는 사람은 Lee 교수에게 문의 바람.

KnowProxy: Adapting Large Language Models by Knowledge-guided Proxy

A Survey on Memory-Efficient Fine-Tuning for Large Language Models

Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment

Connecting the Knowledge Dots: Retrieval-augmented Knowledge Connection for Commonsense Reasoning

“Going to a trap house” conveys more fear than “Going to a mall”: Benchmarking Emotion Context Sensitivity for LLMs

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean

Incorporating Domain Knowledge into Materials Tokenization

Curriculum Debiasing: Toward Robust Parameter-Efficient Fine-Tuning Against Dataset Biases

Forward Knows Efficient Backward Path: Saliency-Guided Memory-Efficient Fine-tuning of Large Language Models

Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning

Continual Debiasing: A Bias Mitigation Framework for Natural Language Understanding Systems

MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction

Mentor-KD: Making Small Language Models Better Multi-step Reasoners

MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science

Zero-shot Commonsense Reasoning over Machine Imagination

Moleco: Molecular Contrastive Learning with Chemical Language Models for Molecular Property Prediction

SEED: Semantic Knowledge Transfer for Language Model Adaptation to Materials Science

SparseFlow: Accelerating Transformers by Sparsifying Information Flows

Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning

Coconut: Contextualized Commonsense Unified Transformers for Graph-Based Commonsense Augmentation of Language Models

KOMBO: Korean Character Representations Based on the Combination Rules of Subcharacters

DIVE: Towards Descriptive and Diverse Visual Commonsense Generation

Leap-of-Thought: Accelerating Transformers via Dynamic Token Routing

Improving Bias Mitigation through Bias Experts in Natural Language Understanding

SMoP: Towards Efficient and Effective Prompt Tuning with Sparse Mixture-of-Prompts

Examining a Consistency of Visual Commonsense Reasoning based on Person Grounding

Client-Customized Adaptation for Parameter-Efficient Federated Learning

“Why do I feel offended?” – Korean Dataset for Offensive Language Identification

Dynamic Structure Pruning for Compressing CNNs

Break it Down into BTS: Basic, Tiniest Subword Units for Korean

Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor Network

Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking

Quantized Sparse Training: A Unified Trainable Framework for Joint Pruning and Quantization of DNNs

Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference

Examining the Impact of Adaptive Convolution on Natural Language Understanding

KOAS: Korean Text Offensiveness Analysis System

Handling Out-of-Vocabulary Problem in Hangeul Word Embeddings

Multi-pretraining for Large-scale Text Classification

Adaptive Compression of Word Embeddings

Personalizing Large-scale Text Classification by Modeling Individual Differences

From Text Classification to Keyphrase Extraction for Short Text

Adaptive Convolution for Text Classification

From Small-scale to Large-scale Text Classification

MoCA: A Novel Privacy-preserving Contextual Advertising Platform on Mobile Devices

meChat: In-device Personal Assistant for Conversational Photo Sharing

Learning to Generate Word Representations using Subword Information

Incorporating Word Embeddings into Open Directory Project based Large-scale Classification

Deriving Human Activity from Geo-located Data by Ontological and Statistical Reasoning

MoCA+: Incorporating User Modeling into Mobile Contextual Advertising

Hashtag-based Topic Evolution in Social Media

sigInterface: A Personalized Interface for Intelligent Services

Mobile Contextual Advertising Platform based on Tiny Text Intelligence

sigSocial: A Novel Social Media Aggregation Service using a Tiny Text Intelligence

Utilizing Verbal Intent in Semantic Contextual Advertising

meCurate: Personalized Curation Service using a Tiny Text Intelligence

Utilizing Wikipedia Knowledge in Open Directory Project-based Text Classification

sigAlbum: An Embedded Photo Service using a Tiny Text Intelligence

Joint Multi-grain Topic Sentiment: Modeling Semantic Aspects for Online Reviews

XQStream++: Fast Tuple Extraction Algorithm for Streaming XML Data

EPE: An Embedded Personalization Engine for Mobile Users

Semantic Contextual Advertising based on the Open Directory Project

Semantic Aspect Discovery for Online Reviews

Novel Approaches to Crawling Important Pages Early

Examining the Impact of Data-access Cost on XML Twig Pattern Matching

Handling Selfishness in Replica Allocation over a Mobile Ad Hoc Network

EUI: An Embedded Engine for Understanding User Intents from Mobile Devices

A Binary String Approach for Updates in Dynamic Ordered XML Data

Novel Web Page Classification Techniques in Contextual Advertising

On the Efficiency of Secure XML Broadcasting 

XIR: Cache Invalidation Strategy for XML Data in Mobile Environments

Efficient, Energy Conserving Transaction Processing in Wireless Data Broadcast

Performance Evaluation of a Predeclaration-based Transaction Pro

Method and server for text classification using multi-task learning

Portable communication terminal for extracting subjects of interest to the user, and a method therefor

Apparatus and method for extracting semantic topic

Server and method for providing content based on context information

Method and apparatus for providing internet service in mobile communication terminal

Method for processing query effectively in radio data broadcast environment

System and method for maintaining cache consistency in a wireless communication system

SangKeun Le

Professor

Data Intelligence Lab.

교수님 소개

이상근

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

KnowProxy: Adapting Large Language Models by Knowledge-guided Proxy

A Survey on Memory-Efficient Fine-Tuning for Large Language Models

Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

이상근

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

KnowProxy: Adapting Large Language Models by Knowledge-guided Proxy

A Survey on Memory-Efficient Fine-Tuning for Large Language Models

Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집