arXiv
Neural Weight Compression for Language Models
Jegwang Ryu, Minkyu Kim, Seungjun Shin, Hee Min Choi, Dokwan Oh, Jaeho Lee
Publications
Preprints
arXiv
Do Reasoning Vision-Language Models Inversely Scale in Test-Time Compute? A Distractor-centric Empirical Analysis
Jiyun Bae, Hyunjong Ok, Sangwoo Mo, Jaeho Lee
arXiv
Activation Quantization of Vision Encoders Needs Prefixing Registers
Seunghyeon Kim, Taesun Yeom, Jinho Kim, Wonpyo Park, Kyuyeun Kim, Jaeho Lee
arXiv
Multi-frame Restoration for High-rate Lissajous Confocal Laser Endomicroscopy
Minhee Lee, Sangyoon Lee, Jiwook Lee, Minki Hong, Kyuyoung Kim, Won Hwa Kim, Jaeho Lee
2026
ICML
Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization
Taesun Yeom, Taehyeok Ha, Jaeho Lee
ACL
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant
Hyunjong Ok, Suho Yoo, Jaeho Lee
ACL Findings
Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models
Hyunjong Ok, Jaeho Lee
ICASSP
Oral
AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?
Hyunjong Ok*, Suho Yoo*, Hyeonjun Kim, Jaeho Lee
DATE
IterQuant: Iterative Quantization Framework for Mixed-Precision LLM Compression
Hyungyo Jeong, Jiwoo Kim, Hyeokjun Kwon, Jaeho Lee, Youngjoo Lee
ICML Workshop: High-Dimensional Learning Dynamics
Generalization Analysis of Linear Knowledge Distillation
Taesun Yeom, Taehyeok Ha, Jaeho Lee
ICML Workshop: High-Dimensional Learning Dynamics
Small for Small: Exploring Optimal Teacher in Knowledge Distillation with Limited Data
Minjae Park, Taesun Yeom, Jaeho Lee
2025
ACL Findings
Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models
Suho Yoo*, Hyunjong Ok*, Jaeho Lee
NAACL
NeurIPS 2024 AFM Workshop
Towards Federated Low-Rank Adaptation with Rank-Heterogeneous Communication
Yuji Byun, Jaeho Lee
ICLR
Fast Training of Sinusoidal Neural Fields via Scaling Initialization
Taesun Yeom*, Sangyoon Lee*, Jaeho Lee
ICLR
ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models
Seonghwan Park, Jaehyeon Jeong, Yongjun Kim, Jaeho Lee, Namhoon Lee
ICASSP
Outstanding paper award @ JKAIA 2024
AudioBERT: Audio Knowledge Augmented Language Model
Hyunjong Ok*, Suho Yoo*, Jaeho Lee
IEEE TNNLS
Communication-Efficient Split Learning via Adaptive Feature-wise Compression
Yongjeong Oh, Jaeho Lee, Christopher G. Brinton, Yo-Seb Jeon
ICLR Workshop: Weight Space Learning
On the Internal Representations of Graph Metanetworks
Taesun Yeom, Jaeho Lee
2024
EMNLP
Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher
Hyunjong Ok, Jegwang Ryu, Jaeho Lee
EMNLP
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
Seungwoo Son, Wonpyo Park, Woohyun Han, Kyuyeun Kim, Jaeho Lee
EMNLP
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization
Sungbin Shin, Wonpyo Park, Jaeho Lee, Namhoon Lee
ECCV
ICLR 2023 Sparsity Workshop Outstanding paper award @ IPIU 2023
The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers
Seungwoo Son, Jegwang Ryu, Namhoon Lee, Jaeho Lee
ICML
Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
Hagyeong Lee*, Minkyu Kim*, Jun-Hyuk Kim, Seungeon Kim, Dokwan Oh, Jaeho Lee
ICML
Hybrid Neural Representations for Spherical Data
Hyomin Kim, Yunhui Jang, Jaeho Lee, Sungsoo Ahn
CVPR
Oral NeurIPS 2023 ATTRIB Workshop
In Search of a Data Transformation that Accelerates Neural Field Training
Junwon Seo*, Sangyoon Lee*, Kwang In Kim, Jaeho Lee
CVPR
Highlight ICML 2023 SCIS Workshop
Discovering and Mitigating Visual Biases through Keyword Explanation
Younghyun Kim*, Sangwoo Mo*, Minkyu Kim, Kyungmin Lee, Jaeho Lee, Jinwoo Shin
NAACL
SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities
Hyunjong Ok, Taeho Kil, Sukmin Seo, Jaeho Lee
IEEE S&P
Few-shot Unlearning
Youngsik Yoon, Jinhwan Nam, Hyojeong Yun, Jaeho Lee, Dongwoo Kim, Jungseul Ok
IEEE IoT Journal
IEEE Communication Theory Workshop 2024
Attention-aware Semantic Communications for Collaborative Inference
Jiwoong Im*, Nayoung Kwon*, Taewoo Park, Jiheon Woo, Jaeho Lee, Yongjune Kim
2023
NeurIPS
ICLR 2023 Neural Fields Workshop
Learning Large-scale Neural Fields via Context Pruned Meta-learning
Jihoon Tack, Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin, Jonathan R. Schwarz
ICML
ICLR 2023 Neural Fields Workshop
Modality-Agnostic Variational Compression of Implicit Neural Representations
Jonathan R. Schwarz, Jihoon Tack, Yee Whye Teh, Jaeho Lee, Jinwoo Shin
TMLR
ICML 2023 SCIS Workshop
Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling
Junhyun Nam, Sangwoo Mo, Jaeho Lee, Jinwoo Shin
NeurIPS
Workshop: UniReps
Semi-Ensemble: A Simple Approach to Over-Parameterize Model Interpolation
Jiwoon Lee, Jaeho Lee
ICML
Workshop: HDLD
On the Effectiveness of Sharpness-aware Minimization with Large Mini-batches
Jinseok Chung, Seonghwan Park, Jaeho Lee, Namhoon Lee
2022
NeurIPS
Scalable Neural Video Representations with Learnable Positional Features
Subin Kim, Sihyun Yu, Jaeho Lee, Jinwoo Shin
NeurIPS
Meta-learning with Self-improving Momentum Targets
Jihoon Tack, Jongjin Park, Hankook Lee, Jaeho Lee, Jinwoo Shin
ICLR
Spread Spurious Attribute: Improving Worst-Group Accuracy with Spurious Attribute Estimation
Junhyun Nam, Jaehyung Kim, Jaeho Lee, Jinwoo Shin
arXiv
Zero-shot Blind Image Denoising via Implicit Neural Representations
Chaewon Kim, Jaeho Lee, Jinwoo Shin
2021
NeurIPS
Meta-learning Sparse Implicit Neural Representations
Jaeho Lee, Jihoon Tack, Namhoon Lee, Jinwoo Shin
COLT
DeepMath 2020 Oral
Provable Memorization via Deep Neural Networks using Sub-linear Parameters
Sejun Park, Jaeho Lee, Chulhee Yun, Jinwoo Shin
ICLR
Spotlight DeepMath 2020 Oral
Minimum Width for Universal Approximation
Sejun Park, Chulhee Yun, Jaeho Lee, Jinwoo Shin
ICLR
Layer-adaptive Sparsity for the Magnitude-based Pruning
Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin
AAAI
MASKER: Masked Keyword Regularization for Reliable Text Generation
Seung Jun Moon, Sangwoo Mo, Kimin Lee, Jaeho Lee, Jinwoo Shin
Sparse Neural Network Workshop
Greedyprune: Layer-wise Optimization Algorithms for Magnitude-based Pruning
Vinoth Nandakumar, Jaeho Lee
2020
NeurIPS
Learning from Failure: Training Debiased Classifier from Biased Classifier
Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, Jinwoo Shin
ICLR
Lookahead: A Far-sighted Alternative of Magnitude-based Pruning
Sejun Park*, Jaeho Lee*, Sangwoo Mo, Jinwoo Shin
Pre-2020
SIMODS
Learning Finite-dimensional Coding Schemes with Nonlinear Reconstruction Maps
Jaeho Lee, Maxim Raginsky
ISIT
On MMSE Estimation from Quantized Observations in the Nonasymptotic Regime
Jaeho Lee, Maxim Raginsky, Pierre Moulin
Domestic Posters
IPIU
An Empirical Study on the Bias of Generative Image Compression
Hagyeong Lee, Jaeho Lee
IPIU
Is Sparse Identification Model Sufficiently Biased?
Junwon Seo, Jaeho Lee