목록으로 돌아가기
4
3
4
52
22
8
교수 프로필
이재호
교수Background
학력
2015~2019
University of Illinois at Urbana-Champaign (박사-Electrical & Computer Engineering)
2016.03 ~ 2019.05
University of Illinois at Urbana - Champaign (박사-Electrical and Computer Engineering)
2013.09 ~ 2015.12
University of Illinois at Urbana - Champaign (석사-Electrical & Computer Engineering)
2009.02 ~ 2013.02
한국과학기술원 (학사-전기 및 전자공학과)
Experience
주요경력
2022 -
POSTECH 전자전기공학과, 조교수
2019 - 2022
한국과학기술원 (KAIST) 연수연구원 / 전문연구요원
2013 - 2013
The Heritage Foundation (Center for Data Analysis) Research Fellow
Publications
학술지
국제전문학술지
CommunicationEfficient Split Learning via Adaptive FeatureWise Compression, IEEE Transactions on Neural Networks and Learning Systems, , 36, 10844-10858 (2025 )
AttentionAware Semantic Communications for Collaborative Inference, IEEE Internet of Things Journal, , 11, 37008-37020 (2024 )
Learning FiniteDimensional Coding Schemes with Nonlinear Reconstruction Maps, Siam Journal on Mathematics of Data Science, , 1, 617-642 (2019 )
일반학술지
Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling, Transactions on Machine Learning Research (TMLR), , , - (2023 )
Conference
학술회의논문
S2Cap A Benchmark and a Baseline for Singing Style Captioning, CIKM 2025 Proceedings of the 34th ACM International Conference on Information and Knowledge Management, , 0, 6492-6497 (2025)
Why Image Codecs Fails for LLM Weight Compression An Empirical Analysis, , , 0, - (2025)
Overthinking Leads to Bias in Visual Reasoning Models, , , 0, - (2025)
Understanding the Effect of Batch Size in LoRA Training, , , 0, - (2025)
Prefixbased Outlier Control for PostTraining Quantization of Image Encoder, , , 0, - (2025)
MIRA A Realtime Multiframe Restoration Framework for LissajousScanned Confocal Endomicroscopy, , , 0, - (2025)
Optimal Richness through the Lens of Task Difficulty, , , 0, - (2025)
Images or Tokens Compressing Visual Inputs of VisionLanguageAction Models for Efficient Communication, , , 0, - (2025)
Do Video Language Models Really Know Where to Look Diagnosing Attention Failures in Video Language Models, , , 0, - (2025)
Imagine to Hear Auditory Knowledge Generation can be an Effective Assistant for Language Models, , , 0, - (2025)
Promptbased Depth Pruning of Large Language Models, Proceedings of Machine Learning Research, , 0, 65936-65948 (2025)
Diffusion 모델 기반 AI Inpainting 이미지의 탐지 및 조작 영역 판별에 관한 연구, , , 0, - (2025)
Towards Federated LowRank Adaptation with RankHeterogeneous Communication, , , 0, - (2025)
ZIP AN EFFICIENT ZEROTHORDER PROMPT TUNING FOR BLACKBOX VISIONLANGUAGE MODELS, 13th International Conference on Learning Representations ICLR 2025, , 0, 4355-4388 (2025)
FAST TRAINING OF SINUSOIDAL NEURAL FIELDS VIA SCALING INITIALIZATION, 13th International Conference on Learning Representations ICLR 2025, , 0, 78800-78842 (2025)
AudioBERT Audio Knowledge Augmented Language Model, ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, , 0, - (2025)
Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher, , , 0, 12460-12476 (2024)
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization , , , 0, - (2024)
Rethinking Pruning Large Language Models Benefits and Pitfalls of Reconstruction Error Minimization, , , 0, - (2024)
The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers, , , 0, 379-396 (2024)
Hybrid Neural Representations for Spherical Data, Proceedings of Machine Learning Research, , 0, 23972-23985 (2024)
Neural Image Compression with Textguided Encoding for both Pixellevel and Perceptual Fidelity, Proceedings of Machine Learning Research, , 0, 26715-26730 (2024)
Discovering and Mitigating Visual Biases through Keyword Explanation, 2024 IEEECVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), , 0, 11082-11092 (2024)
In Search of a Data Transformation that Accelerates Neural Field Training, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, , 0, 4830-4839 (2024)
SCANNER KnowledgeEnhanced Approach for Robust Multimodal Named Entity Recognition of Unseen Entities, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies NAACL 2024, , 0, 7718-7730 (2024)
Fewshot Unlearning, 45TH IEEE SYMPOSIUM ON SECURITY AND PRIVACY SP 2024, , 0, 3276-3292 (2024)
Learning Largescale Neural Fields via Context Pruned MetaLearning, Advances in Neural Information Processing Systems, , 0, - (2023)
A 710b Programmable CryoCMOS TISAR ADC for Multichannel Qubit Readout with OnChip Background InterChannel Mismatch Calibrations, IEEE 49TH EUROPEAN SOLID STATE CIRCUITS CONFERENCE ESSCIRC 2023, , 0, 169-172 (2023)
ModalityAgnostic Variational Compression of Implicit Neural Representations, Proceedings of Machine Learning Research, , 0, 30342-30364 (2023)
Scalable Neural Video Representations with Learnable Positional Features, ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), , 0, - (2022)
MetaLearning with Selfimproving Momentum Target, Advances in Neural Information Processing Systems, , 0, - (2022)
Spread Spurious Attribute Improving Worstgroup Accuracy with Spurious Attribute Estimation, International Conference on Learning Theory, , 0, - (2022)
Metalearning Sparse Implicit Neural Representations, Advances in Neural Information Processing Systems, , 0, 11769-11780 (2021)
Co2L Contrastive Continual Learning, Proceedings of the IEEE International Conference on Computer Vision, , 0, 9496-9505 (2021)
Provable Memorization via Deep Neural Networks using Sublinear Parameters, Proceedings of Machine Learning Research, , 0, 3627-3661 (2021)
Minimum Width for Universal Approximation , ICLR 2021 9th International Conference on Learning Representations, , 0, - (2021)
Layeradaptive Sparsity for the Magnitudebased Pruning, ICLR 2021 9th International Conference on Learning Representations, , 0, - (2021)
MASKER Masked Keyword Regularization for Reliable Text Generation, , , 0, - (2021)
Learning Bounds for Risksensitive Learning, Advances in Neural Information Processing Systems, , 0, - (2020)
Learning from Failure Training Debiased Classifier from Biased Classifier, Advances in Neural Information Processing Systems, , 0, - (2020)
Lookahead A Farsighted Alternative of Magnitudebased Pruning, , , 0, - (2020)
Minimax statistical learning with Wasserstein distances, Advances in Neural Information Processing Systems, , 0, 2687-2696 (2018)
On MMSE estimation from quantized observations in the nonasymptotic regime, IEEE International Symposium on Information Theory Proceedings, , 0, 2924-2928 (2015)
AudioBERT Audio Knowledge Augmented Language Model, , , 0, - (2024)
Towards Federated LowRank Adaptation of Language Models with Rank Heterogeneity, , , 0, - (2024)
Fast Training of Sinusoidal Neural Fields via Scaling Initialization, , , 0, - (2024)
Massive Activations of StateSpace Models A Preliminary Take, , , 0, - (2024)
Limitations of Hessianbased pruning on Mamba, , , 0, - (2024)
DSP Distill the Knowledge Only By a Subset of Patches, , , 0, - (2023)
An Empirical Study on the Bias of Generative Image Compression, , , 0, - (2023)
Debiased Distillation through Feature Distillation, , , 0, - (2023)
Is Sparse Identification Model Sufficiently Biased, , , 0, - (2023)
Highlights
연구실적
Meta-Learning Sparse Implicit Neural Representations Advances in Neural Information Processing Systems (NeurIPS) 2021
Layer-Adaptive Sparsity for the Magnitude-based Pruning International Conference on Learning Representations (ICLR) 2021
Minimum Width for Universal Approximation International Conference on Learning Representations (ICLR spotlight) 2021
Provable Memorization via Deep Neural Networks using Sub-linear Parameters Conference on Learning Theory (COLT) 2021
MASKER: Masked Keyword Regularization for Reliable Text Classification AAAI Conference on Artificial Intelligence (AAAI) 2021
자체연구개발과제, 포항공과대학교 (2024-2044)
이재호 신규부임교수 초기정착비(3차)/대학, 포항공과대학교 (2024-2025)
최적화비용-효율적인 인공신경망 최적화, 재단법인한국연구재단 (2024-2025)
네이버/인텔- 포스텍 극한효율 기계학습 연구센터, 네이버클라우드 주식회사 (2024-2025)
추론 가속을 위한 모델 내 데이터 압축 기술 연구, 삼성전자(주) (2024-2025)
이재호 신규부임교수 초기정착비(2차/학과), 포항공과대학교 (2023-2024)
이재호 신규부임교수 초기정착비(2차/대학), 포항공과대학교 (2023-2024)
최적화비용-효율적인 인공신경망 최적화, 재단법인한국연구재단 (2023-2024)
[UGRP]개인 맞춤형 여행 경로 최적화 알고리즘, 포항공과대학교 (2023-2024)
언어기반 인공지능모델을 활용한 시각신호 압축기법, 삼성전자(주) (2023-2024)
(전사) 신경망 기반 데이터 압축기법의 편향성 해결 연구 및 포스코그룹 활용 제안 (1/1), 포스코홀딩스(주) (2023-2024)
[4.27211_기술개발](전사) 신경망 기반 데이터 압축기법의 편향성 해결 연구 및 포스코그룹 활용 제안 (1/1), 포항공대산학협력단 (2023-2024)
최소침습 뇌종양 수술용 리사주 스캐닝 초소형 의료기기..., 중소기업기술정보진흥원 (2024-2024)
이재호 신규부임교수 초기정착비(1차_학과), 포항공과대학교 (2022-2023)
이재호 신규부임교수 초기정착비(1차_대학), 포항공과대학교 (2022-2023)
신경망 기반 데이터 압축기법의 편향성 계측 및 해결, 재단법인한국연구재단 (2022-2023)
암수술실 현장형 디지털 조직 검사용 리사주(LISSAJOUS) 스캐닝 초소형 프로브의 10HZ 고속 촬영 기반 2 ΜM급 해상도 확보를 위한 인공지능 기반 INTERPOLATION 기술 예비 연구 개발, 중소기업기술정보진흥원 (2023-2023)
Intellectual Property
IP
이재호,류제광,신승준,최희민,오도관, 가중치 행렬 압축 방법 및 장치, 한국, 10-2025-0195257 (IP25)
이재호,이상윤,염태선, 정현파 뉴럴 필드의 학습 가속화를 위한 가중치 스케일링 기반 초기화 기법 및 학습 기술, -, PCT/KR2025/0215 (IP25)
이재호,류제광,오도관,신승준,최희민, 인공신경망 기반 모델 압축 알고리즘, 한국, 10-2025-0132987 (IP25)
이남훈,박성환,정재현,김용준,이재호, 프롬프트를 이용하여 블랙박스 인공지능 모델을 학습시키기 위한 전자 장치 및 이의 동작 방법, 한국, 10-2025-0073518 (IP24)
이재호,이하경,김민규,김준혁,오도관,김승언, 이미지 인코딩 장치 및 방법, 및 이미지 디코딩 장치, 한국, 10-2024-0009324 (IP24)
이재호,변유지,이하경,손승우, 이미지를 복원하기 위한 방법 및 장치, 한국, 10-2024-0020643 (IP23)
이남훈,박성환,정재현,김용준,이재호, 프롬프트를 이용하여 블랙박스 인공지능 모델을 학습시키기 위한 전자 장치 및 이의 동작 방법, USA, 19/380,699 (P202)
이재호,이하경,김민규,김준혁,오도관,김승언, 이미지 인코딩 장치 및 방법, 및 이미지 디코딩 장치, USA, 18/808,909 (P202)