IDEA Lab.

20241004
LLM with Prof.

이성은

• RNN & LSTM

정한교

• Seq2Seq & Attention

신윤섭

• Transformer

이해영

• Speech & Vision Transformer

김초은

• GPT1,2,3 + LLM(In-context learning)

박세현

• Transformer-based Multivariat time Series. Foundation model for time series

조영래

• BERT & GPT

이경선

• Multimodal
  

20240829
LLM

이성은

• GPT-2: Language Models are Unsupervised Multitask Learners

정한교

• GPT-3: GLanguage models are few show Learners

김초은

• LLMs are Zero Shot Reasoners

이경선

• CLIP: Learning Transferable Visual Models From Natural Language Supervision

신윤섭

• Stable Diffusion: High-Resolution Image Synthesis with Latent Diffusion Models

정휘창

• Diffusion Model

20240829
LLM

이성은

• GPT-2: Language Models are Unsupervised Multitask Learners

정한교

• GPT-3: GLanguage models are few show Learners

김초은

• LLMs are Zero Shot Reasoners

이경선

• CLIP: Learning Transferable Visual Models From Natural Language Supervision

신윤섭

• Stable Diffusion: High-Resolution Image Synthesis with Latent Diffusion Models

정휘창

• Diffusion Model

20240822
LLM

박세현

• (ViT) AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE (ICLR 2021)

조영래

• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

20240813
LLM

이해영

• Improving Language Understanding by Generative Pre-Training

신윤섭

• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

20240808
LLM

정한교

• Neural Machine Translation by jointly learning to align and translate

박세현

• Attention is all you need

20240806
LLM

김초은

• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network

이해영

• Sequence to Sequence Learning with Neural Networks

20240801
LLM

이경선

• The Evolution of Translation Models: From DNN to Transformer

이성은

• A Critical Review of Recurrent Neural Networks for Sequence Learning

조영래

• Long Short-Term Memory
  

20240321
Fairness

김초은

• Fairness Aware Counterfactuals for Subgroups (NeurIPS 2023)

박세현

• FairFed: Enabling Group Fairness in Federated Learning (AAAI 2023)

정휘창

• A Fair Generative Model Using LeCam Divergence (AAAI 2023)

이경선

• Achieving Counterfactual Fairness for Anomaly Detection PAKDD 2023

이지후

• Fair Representation Learning for Recommendation: A Mutual Information Perspective (AAAI 2023)
• SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification (AAAI 2023)

20240222
Fairness

김초은

• Loss Balancing for Fair Supervised Learning (ICML 2023)

박세현

• Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks (ICML 2023)

정휘창

• Fair Neighbor Embedding (ICML 2023)

정한교

• On the Within-Group Fairness of Screening Classifiers (ICML 2023)

박진원

• Balanced Fair K-Means Clustering (IEEE 2023)
  

20240119
Fairness

이경선

• ICLR 2023 FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data

정휘창

• ICML 2023 Differential Privacy has Bounded Impact on Fairness in Classification

김초은

• Adapting fairness interventions to missing values

박진원

• ICML 2023 Approximation Algorithms for Fair Range Clustering

20240108
2023 NeurIPS

이경선

• TabMT: Generating tabular data with masked transformers

이지후

• Flat Seeking Bayesian Neural Networks

김초은

• Tree of Thoughts: Deliberate Problem Solving with Large Language Models

박찬무

• Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions

신윤섭

• Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

박유하

• Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

박진원

• Students Parrot Their Teachers: Membership Inference on Model Distillation

박석훈

• Feature learning for interpretable , performant decisition treess

정휘창

• Causal normalizing flows: from theory to practice

최성식

• A Measure-Theoretic Axiomatisation of Causality

정한교

• Are Emergent Abilities of Large Language Models a Mirage?

박세현

• Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization

공인성

• A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning

김건웅

• FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-trained Models in Few-Shot Learning

20231219
XAI

조영래

• Dividing and Conquering a BlackBox to a Mixture of Interpretable Models
• Label free explainability for unsupervised model

박찬무

• Explainability as statistical inference
• Learning_Perturbation

김건웅

• Identifying Interpretable Subspaces in Image
• Visual Classification via Description from

박석훈

• Interpretable GAN
• ProtoVAE

최성식

• Inducing Causal Structure for Interpretable Neural Networks
• Neural Basis Models for Interpretability

신윤섭

• Natural Posterior Network Deep Bayesian Uncertainty for Exponential Family Distribution
• Towards Trustworthy Explanation On Causal Rationalization

20230130
Fairness

박석훈

• Fair Bayes-Optimal classifiers under predictive parity

정연호

• Counterfactual Fairness with Partially Known Causal Graph

양동윤

• On the Tradeoff Between Robustness and Fairness

정휘창

• Fair and Efficient Allocations Without Obvious Manipulations

최성식

• Fairness without Demographics through Knowledge Distillation

김건웅

• Domain Adaptation meets Individual Fairness. And they get along
• Optimal Transport of Classifiers to Fairness

박진원

• Transferring Fairness under Distribution Shifts via Fair Consistency Regularization

이지후

• Fairness Reprogramming

박유하

• Fair Ranking with Noisy Protected Attributes

박세현

• Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

박찬무

• Conformalized Fairness via Quantile Regression
  

이종진

• Self-Supervised Fair Representation Learning without Demographics

김성현

• Fairness Transferability Subject to Bounded Distribution Shift

이경선

• Pushing the limits of fairness impossibility: Who’s the fairest of them all?

20220117
Overparameterization

박유하

• Benign overfitting in linear regression

정휘창

• Benign overfitting in ridge regression

김건웅

• Just interpolate: Kernel “ridgeless” regression can generalize

박진원

• On uniform convergence and low-norm interpolation learning

최성식

• Exact gap between generalization error and uniform convergence in random feature models

이종진

• Uniform convergence of interpolators: Gaussian width, norm bounds, and benign overfitting

공인성

• In defense of uniform convergence: Generalization via derandomization with an application to interpolating predictors

박석훈

• Minimum ℓ1-norm interpolators: Precise asymptotics and multiple descent

이지후

• A random matrix analysis of random fourier features: beyond the gaussian kernel, a precise phase transition, and the corresponding double descent

양동윤

• Generalization of two-layer neural networks: An asymptotic viewpoint
  

20220114

최성식

• Some Methods for Estimating CATE

20210719

공인성

• Approximate function with DNN

20211109

최성식

• Causal paper review

20210719

이종진

• Review of Sparsity

20210716

양동윤

• Review of Fair Clustering Papers

20210520

박석훈

• Implicit regularization in deep matrix factorization

박진원

• Kernel and rich regimes in overparametrized models

이지후

• Implicit bias of gradient descent for wide two-layer neural networks Trained with the Logistic Loss

박유하

• The implicit bias of depth, How incremental learning drives generalization

이종진

• A unifying view on implicit bias in training linear neural networks

20210513

정휘창

• Implicit regularization in matrix factorization

김건웅

• Characterizing Implicit Bias in Terms of Optimization Geometry

최성식

• Implicit Bias of Gradient Descent on Linear Convolutional Networks

양동윤

• Gradient descent aligns the layers of deep linear networks

공인성

• The Implicit Bias of Gradient Descent on Separable Data

20210216

최성식

• Ranking problem

20200907

양동윤

• Class activation map

이종진

• Neural network pruning

20200829

문상준

• Unconstrained convex optimization through first-order approximation methods

20200825

이종진

• Practical Secure Aggregation for Privacy-Preserving Machine Learning (Ch 4, 5)

20200804

김사라

• Individual Fairness AI Reviews

20200729

공인성

• Practical Secure Aggregation for Privacy-Preserving Machine Learning (Ch 3.2, 3.4)

김건웅

• Practical Secure Aggregation for Privacy-Preserving Machine Learning (Ch 3.3, 3.5, and 3.6)
  

20200715

이종진

• Practical Secure Aggregation for Privacy-Preserving Machine Learning

정휘창

• Abstract Algebra

20200702

김사라

• Constrained Fairness AI Reviews

최용찬

• Counterfactual Fairness

20200606

채민우

• Introduction to Hamiltonian Monte Carlo methods

20200516

양동윤

• Review of DeLiGAN:Generative Adversarial Networks for Diversed and Limited Data

최용찬

• VEEGAN : Reducing Mode Collapse in GANs using Implicit Variational Learning

이종진

• Bayesian GAN

김건웅

• Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images

공인성

• Mixture of GANs for Clustering

김성현

• On GANs and GMMs

정휘창

• Mixture Density Generative Adversarial Networks

백규승

• PROBGAN: Towards probabilistic GAN with theoretical guarantees

예성주

• Variational Bayesian GAN

최용찬

• Label-removed generative adversarial networks incorporationg with K-Means

최성식

• A Style-Based Generator Architecture for Generative Adversarial Networks

20200107

이종진

• Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec

백규승

• Learning Sparse DNN Architecture
  

20200103

이상엽

• Adam, AMSGrad, AdamX

20190909

이상엽

• Sparse VAE

백규승

• Generalization error bound – via Compressing Deep Neural Network

최용찬

• Semi-supervised learning with MixUp method – ICT

김사라

• Data Augmentation Reviews

20190708

이상엽

• Approximation and Estimation for High-Dimensional Deep Learning Networks
• Risk Bounds for High-dimensional Ridge Function Combinations Including Neural Networks
• Spectrally-normalized Margin Bounds for Neural Networks

백규승

• On Tighter Generalization Bounds for Deep Neural Networks: CNNs, ResNets, and Beyond
• Size-Independent Sample Complexity of Neural Networks

20190701

서지인

• A Survey of Algorithms and Analysis for Adaptive Online Learning
  

20190603

김보영

• A generalized online mirror descent with applications to classification and regression

김사라

• Adaptive Bound Optimization for Online Convex Optimization

백규승

• Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
• Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization

서지인

• AdaGrad stepsizes : sharp convergence over nonconvex landscapes, from any initialization

20190528

최용찬

• Bayesian clinical trials

김주은

• Bayesian clinical trials
• Bayesian predictive power for interim adaptation in seamless phase II/III trials where the endpoint is survival up to some specied timepoint

공인성

• Use of Bayesian statistics in drug development: Advantages and challenges
• Bayesian design and analysis for clinical trials – a case study and a learner’s perspective

이상엽

• BAYESIAN CLINICAL TRIALS: WHY BOTHER?
• Practical Bayesian Adaptive Randomisation in Clinical Trials

이종진

• A Bayesian adaptive design for clinical trials in rare diseases
• A Bayesian sequential design with adaptive randomization for 2-sided hypothesis test

주여진

• A Bayesian sequential design with binary outcome
• Bayesian apative designs for clinical trials

20190218

이상엽

• SGD 기반 최적화 기법들의 이론적 성질

최용찬

• Explainable AI paper

황재성

• The Solution Of Generalized Lasso For Non Full Rank Case

20190211

온일상

• Sparse variable clustering models

김성현

• Selecting climate change scenarios for regional hydrologic impact studies based on climate extremes indices
  

이종진

• Towards dynamic catchment modelling: a Bayesian Hierarchical mixtures of experts framework

20190125
워크샵

황재성

• Exact Solution Path Algorithm Of Generalized Lasso For Non Full Rank Case

이상엽

• SGD 기반 최적화 기법들의 이론적 성질

김사라

• Outcome uncertainty and attendance demand in sport: the case of English soccer

백규승

• Document Modeling with Gated Recurrent Neural Network for Sentiment Classification
• Attention-based LSTM for Aspect-level Sentiment Classification

김성현

• Attention Networks for Aspect-Level Sentiment Classification

이종진

• Hierarchical Attention Networks for Document Classification
• Semisupervised Autoencoder for Sentiment Analysis

20190115
Recommender seminar with 라인 플러스, TL AI DEV팀

최용찬

• Causal Embeddings for Recommendation

김주은

• Generation Meets Recommendation: Proposing Novel Items for Groups of Users

백규승

• Origin of Native FTRL-Proximal

주여진

• Impact of Item Consumption on Assessment of Recommendations in User Studies

김호철

• Translation-based Factorization Machines for Sequential Recommendation

20181228

김사라

• Reviews of DeepLDA

20181207
Recommender seminar with 라인 플러스, TL AI DEV팀

김보영

• Unbiased Online Recommender Evaluation for Missing-Not-At-Random Implicit Feedback

김사라

• Adaptive Collaborative Topic Modeling for Online Recommendation

서지인

• Spectral Collaborative Filtering
  

유찬우

• Explore, exploit, and explain_ personalizing explainable recommendations with bandits
• HOP-rec_ high-order proximity for implicit recommendation

20181207
Recommender seminar with 라인 플러스, TL AI DEV팀

김보영

• Unbiased Online Recommender Evaluation for Missing-Not-At-Random Implicit Feedback

김사라

• Adaptive Collaborative Topic Modeling for Online Recommendation

서지인

• Spectral Collaborative Filtering
  

유찬우

• Explore, exploit, and explain_ personalizing explainable recommendations with bandits
• HOP-rec_ high-order proximity for implicit recommendation

20181115

이상엽

• Learning AND-OR Templates for Object Recognition and Detection

김주은

• Visualizing and Understanding Convolutional Networks

주여진

• “Why Should I Trust You?” Explaining the Predictions of Any Classifier
  

이종진

• Generating Visual Explanations

김성현

• Attentive Explanations: Justifying Decisions and Pointing to the Evidence

최용찬

• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning models

김보영

• Interpretable classifiers using rules and bayesian Analysis: building a better stroke prediction model
• Human-level concept learning through probabilistic program induction

20181017

백규승

• Mirror descent, Hedge

이상엽

• Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization

minimax seminar
김경희 교수님

20181006

• Minimax lower bounds I
  

20181013

• Minimax bounds II
  

20181201

• Minimax bounds III
  

20181208

• Minimax bounds IV

20180921

김성현

• Online Incremental Feature Learning with Denoising Autoencoders

이상엽

• Bayesian Incremental Learning for Deep Neural Networks

김사라

• Error-Driven Incremental Learning in Deep Convolutional Neural Network for Larg-Scale Image Classification
  

최용찬

• Evolutive deep models for online learning on data streams with no storage

백규승

• Incremental Training of Deep Convolutional Neural Networks
• Online Deep Learning: Learning Deep Neural Networks on the Fly

20180809

이상엽

• Anomaly Detection: A Survey

이종진

• Outlier Detection for Temporal DATA: A Survey

이지수

• A survey of outlier detection
  

김사라

• Deep autoencoding gaussian mixture model for unsupervised anomaly detection

최용찬

• Semi-Supervised Anomaly Detection

20180726 Recommender seminar with 네무스텍(Nemustech)

윤철환

• AD Click Prediction a View from the Trenches

유찬우

• DEEP NEURAL NETWORKS FOR YOUTUBE RECOMMENDATIONS

이지홍

• Related Pins at Pinterest: The Evolution of a Real-World Recommender System
  

정구환

• Online Learning to Rank in Stochastic Click Models
  

20180705

정구환

• Slice Samplers for DPM
• Hamiltonian Monte Carlo and Langevin Monte Carlo
• Factor Graphs, the Sum-Product Algorithm and TrueSkillTM

백규승

• Neural Network Learning: Theoretical Foundation
• Learning by Mirror Averaging

김동하

• Understanding deeply and improving VAT
  
• Generative Auto Encoder

20180628 Recommender seminar with 네무스텍(Nemustech)

서지인

• Click-through Prediction for Advertising in Twitter Timeline
• Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks

최용찬

• CTR prediction models

20180426

이상엽

• DeepDocClassifier: Document Classification with Deep Convolutional Neural Network

김성현

• Distributed Representations of Sentences and Documents

최용찬

• Document context language models
  
• Document embedding with Paragraph vectors

김사라

• Efficient Vector Representation for Documents through Corruption
• Document Embeddings via Recurrent Language Models

김보영

• Hierarchical Recurrent Neural Network for Document Modeling

김동하

• Document Embeddings

이종진

• Classify of Select: Neural Architectures for Extractive Document Summarization

백규승

• From Word Embeddings To Document Distances
• Hierarchical Deep Learning for Text Classication

정구환

• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

최세민

• Multi-Task Learning for Document Ranking and Query Suggestion
• Hierarchical Multiscale Recurrent Neural Networks

20180425 Recommender seminar with 네무스텍(Nemustech)

김호철

• Factorization Machines, Field-aware Factorization Machines

유찬우

• Simple and Scalable Response Prediction for Display Advertising

김보영

• Web-Scale Bayesian Click-Through Rate Prediction for Sponsored Search Advertising in Microsoft’s Bing Search Engine
  
• adPredictor and Message Passing

이종진

• Coupled Group Lasso for Web-Scale CTR Prediction in Display Advertising

김사라

• Personalized click prediction in sponsored search

20180202

정구환

• Wide and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning

김사라

• PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs

서지인

• Hierarchical Attentive Recurrent Tracking(HART)
  

최세민

• Dilated Recurrent Neural Networks

온일상

• MaskRNN: Instance level video object segmentation

이종진

• Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks

백규승

• Z-Forcing: Training Stochastic Recurrent Networks

김보영

• Gated Recurrent Convolution Neural Network for OCR

최용찬

• Learning Hierarchical Information Flow with Recurrent Neural Modules

김동하

• Cortical microcircuits as gated-recurrent neural networks

Recommender seminar with 네무스텍(Nemustech)

논문

• Deep Learning based Recommender System: A Survey and New Perspectives

20171122
이종진

• Multilayer Perceptron based Recommender System

20171122
김보영

• Autoencoder based Recommendation System
  

20171128
서지인

• Convolutional Neural Network based Recommender System

20171226
최용찬

• Recurrent Neural Network based Recommender System

20171226
이지수

• Learning deep structured semantic models for web search using clickthrough data

20180124
정구환

• Restricted Boltzmann Machine based Recommender System

20180124 유찬우

• NADE, GAN Recommender

20180108

최세민

• Introduction to GAN variants

20171129

최세민

• Capsule Networks

20171021

온일상

• Mixture models with a prior on the number of components

백규승

• On the Expressive Power of Deep Neural Networks

김사라

• Building Disease Detection Algorithms with Very Small Numbers of Positive Samples
  

김보영

• Instacart 장바구니 자료 분석

20170731

정구환

• Recommendation with Non-Random Missing Data

20170722

김동하

• Deep Decision Network for Multi-Class Image Classification

최세민

• Generative Adversarial Nets

20170714

김동하

• Supervised learning exploiting clustering information

온일상

• Adaptive Face Verication
  

최세민

• Introduction to face verification
  

20170708

백규승

• Learnable pooling with context Gating for video classification

20170703

김동하

• Neural Machine Translation, Answer Sentence Selection

최세민

• Deep Learning Models for Information Retrieval

김보영

• Next Basket Recommendation
  

황참이

• Generalized Additive Model

전종준

• Primal path algorithm for compositional data analysis

20170519

김보영

• Google Cloud & YouTube-8M Video Understanding Challenge

*회의록

• 20170519 회의록

20170511

김성현

• Google Cloud & YouTube-8M Video Understanding Challenge

백규승

• Exploratory data analysis of labels

20170504

김사라

• YouTube-8M:A Large-Scale Video Classification Benchmark
• YouTube-8M:A Large-Scale Video Classification

김성현

• Google Cloud & YouTube-8M Video Understanding Challenge

김보영

• Learning without forgetting
  

백규승

• Saliency Detection by Multi-Context Deep Learning
• Exploratory data analysis of labels

최세민

• Hierarchical Multi-Label Classification Using Local Neural Networks

최용찬

• ImageNet Classication with Deep Convolutional Neural Networks
  

20170414 네트워크 시각화

황참이

• Glossary of terms

김성현

• Network Cohesion & Graph Partitioning

최용찬

• 자료와 코드
  

20170303 GS-Shop

김동하

• 딥러닝에서의 준 지도 학습법에 관한 연구

최세민

• Personalized Regression for Recommender System

김보영

• Recommender System and Data Analysis
  

정구환

• 토픽모형을 이용한 마이크로 세그멘테이션

온일상

• Sparse Bayesian factor analysis

20170110

김보영

• Autoencoder for Collaborative Filtering
• A non-IID Framework for Collaborative Filtering with Restricted Boltzmann Machines

김동하

• Some discovery of deep learning

김성현

• DNN & visualization in R
  

온일상

• Quantifying lagged effects with a fused lasso penalty
• Sparse factor models with IBP prior

정구환

• Hamiltonian Monte Carlo
• Trueskill

김사라

• Self Consistency

최세민

• Sparse CCA via Precision Adjusted Iterative Thresholding

조성현

• Comparison of Ridge Penalized Logistic Model and Ridge Penalized Simple Linear model in Dichotomous response

백규승

• Wavelets and high order numerical differentiation

20161203

고세윤

• Active Learning

김보영

• Content-Aware Point of Interest Recommendation on Location-Based Social Networks
• Restricted Boltzmann Machines for Collaborative Filtering

김사라

• Explaining Nonlinear Classification Decisions with Deep Taylor Decomposition
  

정구환

• Expectation Propagation
• Undirected Topic Models

온일상

• Measuring Invariances in Deep Networks

권용찬

• 3D Multiscale Residual U-Net Architecture for Brain Lesion Segmentation

최세민

• Semi-supervised learning and clustering using deep structure literature review
• Variants of Canonical Correlation Analysis

백규승

• Visualizing and Understanding Convolutional Networks

김성현

• Visualizing Higher-Layer Features of a Deep Network