Jaeho Lee

CoRR, February, 2026

2025

Do Reasoning Vision-Language Models Inversely Scale in Test-Time Compute? A Distractor-centric Empirical Analysis.

[BibT_eX]

[DOI]

CoRR, November, 2025

Neural Weight Compression for Language Models.

[BibT_eX]

[DOI]

CoRR, October, 2025

Post-training quantization of vision encoders needs prefixing registers.

[BibT_eX]

[DOI]

CoRR, October, 2025

AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

[BibT_eX]

[DOI]

CoRR, September, 2025

Do Video Language Models Really Know Where to Look? Diagnosing Attention Failures in Video Language Models.

[BibT_eX]

[DOI]

CoRR, September, 2025

Communication-Efficient Split Learning via Adaptive Feature-Wise Compression.

[BibT_eX]

[DOI]

Yongjeong Oh

Christopher G. Brinton

Yo-Seb Jeon

IEEE Trans. Neural Networks Learn. Syst., June, 2025

Speculative End-Turn Detector for Efficient Speech Chatbot Assistant.

[BibT_eX]

[DOI]

Suho Yoo

CoRR, March, 2025

On the Internal Representations of Graph Metanetworks.

[BibT_eX]

[DOI]

Taesun Yeom

CoRR, March, 2025

Towards Federated Low-Rank Adaptation of Language Models with Rank Heterogeneity.

[BibT_eX]

[DOI]

Yuji Byun

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Prompt-based Depth Pruning of Large Language Models.

[BibT_eX]

[DOI]

Juyun Wee

Minjae Park

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Fast Training of Sinusoidal Neural Fields via Scaling Initialization.

[BibT_eX]

[DOI]

Taesun Yeom

Sangyoon Lee

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

AudioBERT: Audio Knowledge Augmented Language Model.

[BibT_eX]

[DOI]

Suho Yoo

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

S2Cap: A Benchmark and a Baseline for Singing Style Captioning.

[BibT_eX]

[DOI]

Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025

Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models.

[BibT_eX]

[DOI]

Suho Yoo

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Attention-Aware Semantic Communications for Collaborative Inference.

[BibT_eX]

[DOI]

IEEE Internet Things J., November, 2024

Constructing a Singing Style Caption Dataset.

[BibT_eX]

[DOI]

CoRR, 2024

Towards Federated Low-Rank Adaptation with Rank-Heterogeneous Communication.

[BibT_eX]

[DOI]

Yuji Byun

CoRR, 2024

Few-shot Unlearning.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Hybrid Neural Representations for Spherical Data.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher.

[BibT_eX]

[DOI]

Jegwang Ryu

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

In Search of a Data Transformation that Accelerates Neural Field Training.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Discovering and Mitigating Visual Biases Through Keyword Explanation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

Debiased Distillation by Transplanting the Last Layer.

[BibT_eX]

[DOI]

Jiwoon Lee

CoRR, 2023

MaskedKD: Efficient Distillation of Vision Transformers with Masked Images.

[BibT_eX]

[DOI]

Seungwoo Son

Namhoon Lee

CoRR, 2023

Efficient Meta-Learning via Error-based Context Pruning for Implicit Neural Representations.

[BibT_eX]

[DOI]

Jonathan Richard Schwarz

CoRR, 2023

Explaining Visual Biases as Words by Generating Captions.

[BibT_eX]

[DOI]

CoRR, 2023

Semi-Ensemble: A Simple Approach Over-parameterize Model Interpolation.

[BibT_eX]

[DOI]

Jiwoon Lee

Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models, 2023

Learning Large-scale Neural Fields via Context Pruned Meta-Learning.

[BibT_eX]

[DOI]

Jonathan Richard Schwarz

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Modality-Agnostic Variational Compression of Implicit Neural Representations.

[BibT_eX]

[DOI]

Jonathan Richard Schwarz

Proceedings of the International Conference on Machine Learning, 2023

2022

Zero-shot Blind Image Denoising via Implicit Neural Representations.

[BibT_eX]

[DOI]

Chaewon Kim

Jinwoo Shin

CoRR, 2022

Meta-Learning with Self-Improving Momentum Target.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Scalable Neural Video Representations with Learnable Positional Features.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Meta-Learning Sparse Implicit Neural Representations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Minimum Width for Universal Approximation.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Layer-adaptive Sparsity for the Magnitude-based Pruning.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Co<sup>2</sup>L: Contrastive Continual Learning.

[BibT_eX]

[DOI]

Hyuntak Cha

Jinwoo Shin

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Provable Memorization via Deep Neural Networks using Sub-linear Parameters.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

MASKER: Masked Keyword Regularization for Reliable Text Classification.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

A Deeper Look at the Layerwise Sparsity of Magnitude-based Pruning.

[BibT_eX]

[DOI]

CoRR, 2020

Learning from Failure: Training Debiased Classifier from Biased Classifier.

[BibT_eX]

[DOI]

CoRR, 2020

Adaptive Learning-Rate Backpropagation Neural Network Algorithm Based on the Minimization of Mean-Square Deviation for Impulsive Noises.

[BibT_eX]

[DOI]

IEEE Access, 2020

Learning from Failure: De-biasing Classifier from Biased Classifier.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning Bounds for Risk-sensitive Learning.

[BibT_eX]

[DOI]

Sejun Park

Jinwoo Shin

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Lookahead: A Far-sighted Alternative of Magnitude-based Pruning.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Robustness and generalization guarantees for statistical learning of generative models

[BibT_eX]

[DOI]

PhD thesis, 2019

Learning Finite-Dimensional Coding Schemes with Nonlinear Reconstruction Maps.

[BibT_eX]

[DOI]

SIAM J. Math. Data Sci., 2019

2018

Minimax Statistical Learning with Wasserstein distances.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017

Minimax Statistical Learning and Domain Adaptation with Wasserstein Distances.

[BibT_eX]

[DOI]

CoRR, 2017

2015

On MMSE estimation from quantized observations in the nonasymptotic regime.

[BibT_eX]

[DOI]