We are a research group headed by Prof. Jaekyun Moon in the School of EE at KAIST (also affiliated with the Graduate School of AI and School of Computing at KAIST). We work on distributed/federated machine learning, robust AI and resource-efficient AI, addressing all key issues in the deployment of practical AI systems

KAIST 전기공학부 문재균 교수님 지도하에 운영되는 연구실입니다(KAIST AI 대학원 및 전산학부 소속). 저희는 분산/연합 머신러닝, 강력한 AI 및 리소스 효율적인 AI를 연구하며, 실제 AI 시스템 구축의 모든 주요 문제를 해결합니다.

ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization

Adaptive Energy Alignment for Accelerating Test-Time Adaptation

Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning

Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration

Federated Split Learning with Joint Personalization-Generalization for Inference-Stage Optimization in Wireless Edge Networks

StableFDG: Style and Attention Based Learning for Federated Domain Generalization

Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

EvoFed: Leveraging Evolutionary Strategies for Efficient and Privacy-Preserving Federated Learning

Improving Low-Latency Predictions in Multi-Exit Neural Networks via Block-Dependent Losses

Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization

Distribution Aware Active Learning via Gaussian Mixtures

Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation

Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning

SplitGP: Achieving Both Generalization and Personalization in Federated Learning

Deep Neural Network Compression for Image Inpainting

Style Balancing and Test-Time Style Shifting for Domain Generalization

Locally Supervised Learning with Periodic Global Guidance

GenLabel: Mixup Relabeling using Generative Models

Training Multi-Exit Architectures via Block-Dependent Losses for Anytime Inference

Active Object Detection with Epistemic Uncertainty and Hierarchical Information Aggregation

CAFENet: Class-Agnostic Few-Shot Edge Detection Network

Few-Round Learning for Federated Learning

Sageflow: Robust Federated Learning against Both Stragglers and Adversaries

FedMes: Speeding Up Federated Learning with Multiple Edge Servers

Accelerating Federated Learning with Split Learning on Locally Generated Losses

Handling Both Stragglers and Adversaries for Robust Federated Learning

Coded Wireless Distributed Computing with Packet Losses and Retransmissions

TiBroco: A Fast and Secure Distributed Learning Framework for Tiered Wireless Edge Networks

Probabilistic Caching and Dynamic Delivery Policies for Categorized Contents and Consecutive User Demands

Hierarchical Broadcast Coding: Expediting Distributed Learning at the Wireless Edge

Characterization of Inter-Cell Interference in 3D NAND Flash Memory

Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks

GAN-mixup: Augmenting Across Data Manifolds for Improved Robustness

XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning

Dynamic Power Allocation and User Scheduling for Power-Efficient and Delay-Constrained Multiple Access Networks

Secure Clustered Distributed Storage Against Eavesdropping

TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

Irregular Product Coded Computation for High-Dimensional Matrix Multiplication

Scalable Network-Coded PBFT Consensus Algorithm

Coded Distributed Computing over Packet Erasure Channels

Coded Matrix Multiplication on a Group-Based Model

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

Improving SSD Read Latency via Coding

Cache Allocations for Consecutive Requests of Categorized Contents: Service Provider's Perspective

Capacity of Clustered Distributed Storage

Probabilistic Caching Policy for Categorized Contents and Consecutive User Demands

Bi-Directional Cooperative NOMA Without Full CSIT

Combined Window-Filter Waveform Design With Transmitter-Side Channel State Information

Wireless Video Caching and Dynamic Streaming Under Differentiated Quality Requirements

Adaptive Detector Selection for Queue-Stable Word Error Rate Minimization in Connected Vehicle Receiver Design

Doppler Channel Series Prediction Using Recurrent Neural Network

LDPC Code Design for Distributed Storage: Balancing Repair Bandwidth, Reliability, and Storage Overhead

A Class of MSR Codes for Clustered Distributed Storage

Hierarchical Coding for Distributed Computing

Meta-Learner with Linear Nulling

On Reusing Pilots Among Interfering Cells in Massive MIMO

Pilot Reuse Strategy Maximizing the Weighted-Sum-Rate in Massive MIMO Systems

Combined Subband-Subcarrier Spectral Shaping in Multi-Carrier Modulation under the Excess Frame Length Constraint

Improving Read Access Time of High-Performance Solid-State Drives via Layered Coding Schemes

Tapnet: Neural network augmented with task-adaptive projection for few-shot learning

Equalization for maximum likelihood detectors

Performance comparison of detection methods in magnetic recording

Maximum transition run codes for data storage systems

Pattern-dependent noise prediction in signal-dependent noise

Digital front-end for wireless communication system

Sageflow: Robust federated learning against both stragglers and adversaries

Accelerating federated learning with split learning on locally generated losses

Apparatus and method for dynamic diversity based upon receiver-side assessment of link quality

Communication-computation efficient secure aggregation for federated learning

Discrete-time modeling of transition noise dominant channels and study of detection performance

Wireless video caching and dynamic streaming under differentiated quality requirements

Error detection and correction using error pattern correcting codes

Warping the space: Weight space rotation for class-incremental few-shot learning

Hierarchical coding for distributed computing

Joint equalization, soft-demapping and phase error correction in wireless system with receive diversity

A low-density generator matrix interpretation of parallel concatenated single bit parity codes

Capacity of clustered distributed storage

Xtarnet: Learning to extract task-adaptive representation for incremental few-shot learning

Signal-to-noise ratio definition for magnetic recording channels with transition noise

Jaekyun Moon

Professor

MoonLab

교수님 소개

문재균

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization

Adaptive Energy Alignment for Accelerating Test-Time Adaptation

ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

문재균

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization

Adaptive Energy Alignment for Accelerating Test-Time Adaptation

ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집