Bokyeong Kim

Kyungsu Kim

Sung-Yub Kim

Hajin Shim

Tehrim Yoon

Geondo Park

Gyeongman Kim

Jihun Yun

June Yong Yang

Youngki Hong

Ingyo Chung

Joonyoung Yi

Wonjun Chung

Yongsu Baek

Juhyuk Lee

Jung Hyun Lee

Soonwoo Kwon

Eunhyouk Shin

Seohui Bae

Sumin Shin

Jonghoon Shin

Youngho Jeong

Changhun Kim

Hyunjin Seo

JungEun Kim

Kyusung Seo

Seungyeon Woo

Taewon Kim

Will Arnold

The Machine Learning and Inference Lab focuses on Machine Learning and Artificial Intelligence research. Machine Learning Algorithms
Multi-Modal Learning
Large Language Models
Computer Vision
Machine Learning
for Healthcare

머신러닝 및 추론 연구실은 머신러닝 및 인공지능 연구에 집중합니다.

Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood

H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis

CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation

Taxonomy of Comprehensive Safety for Clinical Agents

Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens

Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing

VQ-FedDiff: Federated Learning Algorithm of Diffusion Models with Client-Specific Vector-Quantized Conditioning

HybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generation

DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values

R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding

TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation

Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy

Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing

Deep Learning-Based Landmark Detection Model for Multiple Foot Deformity Classification: A Dual-Center Study

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

ReBind: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring

Test-Time Ensemble via Linear Mode Connectivity: A Path to Better Adaptation

Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models

Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping

Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting

LANTERN++: Enhanced Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models

LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices

Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy

AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler

EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries

A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective

PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning

Time Series Classification with Large Language Models via Linguistic Scaffolding

CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation

TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias

PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency

Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images

Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication

TEDDY: Trimming Edges with Degree-based Discrimination strategY

SeamsTalk: Seamless Talking Face Generation via Flow-Guided Inpainting

ProxyDet: Synthesizing Proxy Novel Classes via Classwise Mixup for Open Vocabulary Object Detection

GEX: A flexible method for approximating influence via Geometric Ensemble

Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds

PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label

SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization

ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models

Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation

RGE: A Repulsive Graph Rectification for Node Classification via Influence

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding

Deep Self-Supervised Diversity Promoting Learning on Hierarchical Hyperspheres for Regularization

Towards the Practical Utility of Federated Learning in the Medical Domain

WeavSpeech: Data Augmentation Strategy for Automatic Speech Recognition via Semantic-Aware Weaving

Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance

Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel

Machine-Learning Model for the Prediction of Hypoxaemia during Endoscopic Retrograde Cholangiopancreatography under Monitored Anaesthesia Care

Set Based Stochastic Subsampling

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods

GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification

Model-augmented Prioritized Experience Replay

Online Coreset Selection for Rehearsal-based Continual Learning

Online Hyperparameter Meta-Learning with Hypergradient Distillation

AdaBlock: SGD with Practical Block Diagonal Matrix Adaptation for Deep Learning

A Simple Framework for Robust Out-of-Distribution Detection

Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation

Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing

Learning Polymorphic Neural ODEs with Time-Evolving Mixture

Learning How Long to Wait: Adaptively-Constrained Monotonic Multihead Attention for Streaming ASR

Adaptive Proximal Gradient Methods for Structured Neural Networks

Unbiased Classification through Bias-Contrastive and Bias-Balanced Learning

Compressed Sensing via Measurement-Conditional Generative Models

Distilling Linguistic Context for Language Model Compression

Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss

RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

Lifelong learning with dynamically expandable networks

Learning to propagate labels: Transductive propagation network for few-shot learning

Federated continual learning with weighted inter-client transfer

Federated semi-supervised learning with inter-client consistency & disjoint learning

Fedmix: Approximation of mixup under mean augmented federated learning

Distribution aligning refinery of pseudo-label for imbalanced semi-supervised learning

Graphical models via univariate exponential family distributions

Meta-stylespeech: Multi-speaker adaptive text-to-speech generation

Scalable and order-robust continual learning with additive parameter decomposition

A review of multivariate distributions for count data derived from the Poisson distribution

Graphical Models via Generalized Linear Models

Mixed Graphical Models via Exponential Families

Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks

Asymmetric Multi-task Learning based on Task Relatedness and Loss

Uncertainty-aware attention for reliable interpretation and prediction

On Poisson Graphical Models

Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding

Machine Learning and Intelligence Lab

교수님 소개

양은호

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood

H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis

CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

양은호

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood

H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis

CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집