[C151] Efficient Long Context Language Model Retrieval with Compression

Minju Seo, Jinheon Baek, Seongyun Lee and Sung Ju Hwang, ACL 2025

[paper] 

[C150] VideoRAG: Retrieval-Augmented Generation over Video Corpus

Soyeong Jeong, Kangsan Kim, Jinheon Baek and Sung Ju Hwang, ACL Findings 2025

[paper] 

[C149] SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models

Seanie Lee, Dong Bok Lee, Dominik Wagner, Minki Kang, Haebin Seong, Tobias Bocklet, Juho Lee and Sung Ju Hwang, ACL Findings 2025

[paper] 

[C148] AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

Patara Trirat, Wonyong Jeong and Sung Ju Hwang, ICML 2025

[paper] 

[C147] Bayesian Neural Scaling Laws Extrapolation with Prior-Fitted Networks

Dongwoo Lee, Dong Bok Lee, Steven Adriaensen, Juho Lee, Sung Ju Hwang, Frank Hutter, Seon Joo Kim and Hae Beom Lee, ICML 2025

[paper] 

[C146] VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding

Kangsan Kim, Geon Park, Youngwan Lee, Woongyeong Yeo, Sung Ju Hwang, CVPR 2025

[paper] 

[C145] Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models

Sangwon Jang, June Suk Choi, Jaehyeong Jo, Kimin Lee, Sung Ju Hwang, CVPR 2025

[paper] 

[C144] ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models

Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, Sung Ju Hwang, NAACL 2025

[paper] 

[C143] A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention

Heejun Lee, Geon Park, Youngwan Lee, Jaduk Suh, Jina Kim, Wonyong Jeong, Bumsik Kim, Hyemin Lee, Myeongjae Jeon, Sung Ju Hwang, ICLR 2025

[paper] 

[C142] HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Seanie Lee, Haebin Seong, Dong Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagner, Yoshua Bengio, Juho Lee, Sung Ju Hwang, ICLR 2025

[paper] 

[C141] Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

Seanie Lee, Minsu Kim, Lynn Cherif, David Dobre, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Moksh Jain, ICLR 2025

[paper] 

[C140] Training Free Exponential Context Extension via Cascading KV Cache

Jeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon, Sung Ju Hwang, ICLR 2025

[paper] 

[C139] Diffusion-based Neural Network Weights Generation

Bedionita Soro, Bruno_Andreis, Hayeon Lee, Wonyong Jeong, Song Chong, Frank Hutter, Sung Ju Hwang, ICLR 2025

[paper] 

[C138] KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

Youngwan Lee, Kwanyong Park, Yoorhim Cho, Yong-Ju Lee, Sung Ju Hwang, NeurIPS 2024

[paper] 

[C137] Set-based Neural Network Encoding Without Weight Tying

Bruno Andreis, Soro Bedionita, Philip Torr, Sung Ju Hwang, NeurIPS 2024

[paper (link coming soon)] 

[C136] Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models

Minki Kang, Sung Ju Hwang, Gibbeum Lee, Jaewoong Cho, NeurIPS 2024

[paper (link coming soon)] 

[C135] Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models

Sangwon Jang*, Jaehyeong Jo*, Kimin Lee, Sung Ju Hwang, NeurIPS 2024

[paper] 

[C134] Rethinking Code Refinement: Learning to Judge Code Efficiency

Minju Seo, Jinheon Baek, Sung Ju Hwang, EMNLP 2024

[paper (link coming soon)] 

[C133] Concept-skill Transferability-based Data Selection for Large Vision-Language Models

Jaewoo Lee, Boyang Li, Sung Ju Hwang, EMNLP 2024

[paper] 

[C132] STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment

Jaewoo Lee, Jaehong Yoon, Wonjae Kim, Yunji Kim and Sung Ju Hwang, ICML 2024

[paper] 

[C131] Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

Jaehyeong Jo and Sung Ju Hwang, ICML 2024

[paper] 

[C130] Graph Generation with Diffusion Mixture

Jaehyeong Jo, Dongki Kim and Sung Ju Hwang, ICML 2024

[paper] 

[C129] Drug Discovery with Dynamic Goal-aware Fragments

Seul Lee, Seanie Lee, Kenji Kawaguchi and Sung Ju Hwang, ICML 2024

[paper] 

[C128] BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

Daeun Lee, Jaehong Yoon and Sung Ju Hwang, ICML 2024

[paper] 

[C127] EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

Sunil Hwang, Jaehong Yoon, Youngwan Lee and Sung Ju Hwang, ICML 2024

[paper] 

[C126] One Prompt is not Enough: Automated Construction off a Mixture-of-Experts Prompts

Ruochen Wang, Sohyun An, Minhao Cheng, Tianyi Zhou, Sung Ju Hwang and Cho-Jui Hsieh, ICML 2024

[paper] 

[C125] Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang and Jong C. Park, NAACL 2024

[paper] 

[C124] Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models

Yujin Kim, Jaehong Yoon, Seonghyeon Ye, Sangmin Bae, Namgyu Ho, Sung Ju Hwang and Se-Young Yun, NAACL 2024

[paper] 

[C123] ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning

Beomgyoung Kim, Joonsang Yu and Sung Ju Hwang, CVPR 2024

[paper] 

[C122] SEA: Sparse Linear Attention with Estimated Attention Mask

Heejun Lee, Jina Kim, Jeffrey Willette, and Sung Ju Hwang, ICLR 2024

[paper] 

[C121] DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

Sohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang, ICLR 2024

[paper] 

[C120] Self-Supervised Dataset Distillation for Transfer Learning

Dong Bok Lee*, Seanie Lee*, Joonho Ko, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang, ICLR 2024

(*: equal contribution)

[paper] 

[C119] Progressive Fourier Neural Representation for Sequential Video Compilation

Haeyong Kang, Jaehong Yoon, DaHyun Kim, Sung Ju Hwang and Chang D. Yoo, ICLR 2024

[paper] 

[C118] Learning to Verify Knowledge-Augmented Language Models

Jinheon Baek, Soyeong Jeong, Minki Kang, Jong C. Park and Sung Ju Hwang, EMNLP 2023

[paper] 

[C117] Co-training and Co-distillation for Quality Improvement and Compression of Language Models

Hayeon Lee, Rui Hou, Jongpil Kim, Davis Liang, Hongbo Zhang, Sung Ju Hwang, Alexander Min, Findings of EMNLP 2023

[paper] 

[C116] Test-Time Self-Adaptive Small Language Models for Question Answering

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong C. Park, Findings of EMNLP 2023

[paper] 

[C115] Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Minki Kang, Seanie Lee, Jinheon Baek, Kenji Kawaguchi and Sung Ju Hwang, NeurIPS 2023

[paper] 

[C114] Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations

Hyeonjeong Ha, Minseon Kim and Sung Ju Hwang, NeurIPS 2023

[paper] 

[C113] Effective Targeted Attacks for Adversarial Self-Supervised Learning

Minseon Kim, Hyeonjeong Ha, Sooel Son and Sung Ju Hwang, NeurIPS 2023

[paper] 

[C112] STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection

Sujin Jang, Dae Ung Jo, Sung Ju Hwang, Dongwook Lee, Daehyun Ji, NeurIPS 2023

[paper] 

[C111] Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models

Jaewoong Lee, Sangwon Jang, Jaehyeong Jo, Jaehong Yoon, Yunji Kim, Jin-Hwa Kim, Jung-Woo Ha and Sung Ju Hwang, ICCV 2023

[paper] 

[C110] ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models

Minki Kang, Wooseok Han, Sung Ju Hwang and Eunho Yang, Interspeech 2023

[paper] 

[C109] Direct Fact Retrieval from Knowledge Graphs without Entity Linking
Jinheon Baek, Alham Fikri Aji, Jens Lehmann and Sung Ju Hwang, ACL 2023 (long paper)

[paper] 

[C108] Language Detoxification with Attribute-Discriminative Latent Space
Jinmyung Kwak, Minseon Kim, and Sung Ju Hwang, ACL 2023 (long paper)

[paper] 

[C107] A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Model
Hayeon Lee, Rui Hou, Jongpil Kim, Davis Liang, Sung Ju Hwang and Alexander Min, Findings of ACL 2023

[paper] 

[C106] Phrase Retrieval for Open Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning
Soyeong Jeong, Jinheon Baek, Sung Ju Hwang and Jong C. Park, Findings of ACL 2023

[paper] 

[C105] Exploring Chemical Space with Score-based Out-of-distribution Generation

Seul Lee, Jaehyeong Jo, Sung Ju Hwang, ICML 2023
[paper] 

[C104] Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation

Jeffrey Willette*, Seanie Lee*, Bruno Andreis, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang, ICML 2023

(*: equal contribution)
[paper] 

[C103] Personalized Subgraph Federated Learning

Jinheon Baek, Wonyong Jeong, Jiongdao Jin, Jaehong Yoon, Sung Ju Hwang, ICML 2023
[paper] 

[C102] Margin-based Neural Network Watermarking

Byungjoo Kim, Suyoung Lee, Seanie Lee, Sooel Son, Sung Ju Hwang, ICML 2023
[paper] 

[C101] Continual Learners are Incremental Model Generalizers

Jaehong Yoon, Sung Ju Hwang, and Yue Cao, ICML 2023
[paper] 

[C100] DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
Taesik Gong, Yewon Kim, Adiba Orzikulova, Yunxin Liu, Sung Ju Hwang, UbiComp (IMWUT) 2023

[paper] 

[C99] The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation

Beomyoung Kim, Joonhyun Jeong, Dongyoon Han, Sung Ju Hwang, CVPR 2023
[paper] 

[C98] Any-speaker Adaptive Text-To-Speech Synthesis with Diffusion Models
Minki Kang, Dongchan Min and Sung Ju Hwang, ICASSP 2023

[paper] 

[C97] Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement
Soyeong Jeong, Jinheon Baek, Sung Ju Hwang, Jong C. Park, EACL 2023

[paper] 

[C96] Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets

Hayeon Lee*, Sohyun An*, Minseon Kim and Sung Ju Hwang, ICLR 2023

(*: equal contribution) (notable-top-25% - spotlight)
[paper] 

[C95] Self-Distillation for Further Pre-training of Transformers

Seanie Lee, Minki Kang, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi,  ICLR 2023
[paper] 

[C94] Sparse Token Transformers with Attention Back Tracking

Heejun Lee, Minki Kang, Youngwan Lee and Sung Ju Hwang, ICLR 2023
[paper] 

[C93] Self-Supervised Set Representation Learning for Unsupervised Meta-Learning

Dong Bok Lee*, Seanie Lee*, Kenji Kawaguchi, Yunji Kim, Jihwan Bang, Jung-Woo Ha and Sung Ju Hwang,

(*: equal contribution) ICLR 2023
[paper] 

[C92] Exploring the Role of Mean Teacher in Self-supervised Masked Auto-Encoders

Youngwan Lee*, Jeffrey Ryan Willete*, Jonghee Kim, Juho Lee and Sung Ju Hwang

(*: equal contribution), ICLR 2023
[paper] 

[C91] On the Soft-Subnetwork for Few-Shot Class Incremental Learning

Haeyong Kang, Jaehong Yoon, Sultan Rizky, Hikmawan Madjid, Sung Ju Hwang and Chang D. Yoo, ICLR 2023
[paper] 

[C90] Rethinking the Entropy of Instance in Adversarial Training

Minseon Kim, Jihoon Tack, Jinwoo Shin, and Sung Ju Hwang, SaTML 2023
[paper] 

[C89] Learning to Generate Inversion-Resistant Model Explanations

Hoyong Jeong, Suyoung Lee, Sung Ju Hwang and Sooel Son,  NeurIPS 2022
[paper] 

[C88] Set-based Meta-Interpolation for Few-Task Meta-Learning

Seanie Lee*, Bruno Andreis*, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang (*: equal contribution), NeurIPS 2022
[paper] 

[C87] Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity Matching

Wonyong Jeong and Sung Ju Hwang, NeurIPS 2022
[paper] 

[C86] Graph Self-supervised Learning with Accurate Discrepancy Learning

Dongki Kim*, Jinheon Baek*, Sung Ju Hwang (*: equal contribution), NeurIPS 2022
[paper] 

[C85] Set Based Stochastic Subsampling

Bruno Andreis, Seanie Lee, A. Tuan Nguyen, Juho Lee, Eunho Yang, Sung Ju Hwang, ICML 2022
[paper] 

[C84] Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

Jaehyeong Jo (＊), Seul Lee (＊),  Sung Ju Hwang (＊: equal contribution), ICML 2022
[paper] 

[C83] Forget-free Continual Learning with Winning Subnetworks

Haeyong Kang, Rusty J. L. Mina, Sultan R. H. Madjid, Jaehong Yoon, Chang D. Yoo, Sung Ju Hwang, and Mark Hasegawa-Johnson, ICML 2022
[paper] 

[C82] Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization

Jaehong Yoon*, Geon Park*, Wonyong Jeong, Sung Ju Hwang (*: equal contribution) ICML 2022

[paper] 

[C81] KALA: Knowledge-Augmented Language Model Adaptation

Minki Kang*, Jinheon Baek*, Sung Ju Hwang (*: equal contribution), NAACL 2022
[paper] 

[C80] Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang and Jong C. Park, ACL 2022
[paper] 

[C79] MPViT : Multi-Path Vision Transformer for Dense Prediction

Youngwan Lee, Jonghee Kim, Jeffrey Willette, and Sung Ju Hwang, CVPR 2022
[paper] 

[C78] Rethinking the Representational Continuity: Towards Unsupervised Continual Learning

Divyam Madaan, Jaehong Yoon, Yuanchun Li, Yunxin Liu and Sung Ju Hwang, ICLR 2022 (oral)
[paper] 

[C77] Online Hyperparameter Meta-Learning with Hypergradient Distillation

Hae Beom Lee, Hayeon Lee, JaeWoong Shin, Eunho Yang, Timothy Hospedales and Sung Ju Hwang, ICLR 2022
[paper] 

[C76] Model-augmented Prioritized Experience Replay

Youngmin Oh, Jinwoo Shin, Eunho Yang and Sung Ju Hwang, ICLR 2022
[paper] 

[C75] Online Coreset Selection for Rehearsal-based Continual Learning

Jaehong Yoon, Divyam Madaan, Eunho Yang and Sung Ju Hwang, ICLR 2022
[paper] 

[C74] Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty

Jeffrey Ryan Willette, Hae Beom Lee, Juho Lee and Sung Ju Hwang, ICLR 2022
[paper] 

[C73] Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning

Seanie Lee, Hae Beom Lee, Juho Lee and Sung Ju Hwang, ICLR 2022
[paper] 

[C72] Skill-based Meta-Reinforcement Learning

Taewook Nam, Shao-Hua Sun, Karl Pertsch, Sung Ju Hwang and Joseph J Lim, ICLR 2022
[paper] [project page] 

[C71] Consistency Regularization for Adversarial Robustness

Jihoon Tack, Sihyun Yu, Jongheon Jeong, Minseon Kim, Sung Ju Hwang, Jinwoo Shin, AAAI 2022
[paper] 

[C70] Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing

Joonhyung Park, June Yong Yang, Jinwoo Shin, Sung Ju Hwang, Eunho Yang, AAAI 2022
[paper] 

[C69] Task-Adaptive Neural Network Search with Meta-Contrastive Learning
Wonyong Jeong*, Hayeon Lee*, Geon Park*, Eunyoung Hyung, Jinheon Baek and Sung Ju Hwang, 

NeurIPS 2021 (spotlight) (*: equal contribution)
[paper] 

[C68] Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning
Hayeon Lee*, Sewoong Lee*, Song Chong and Sung Ju Hwang,  NeurIPS 2021 (spotlight)

(*: equal contribution)
[paper] 

[C67] Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding
Andreis Bruno, Jeffrey Ryan Willette, Juho Lee and Sung Ju Hwang,  NeurIPS 2021

[paper] 

[C66]  Edge Representation Learning with Hypergraphs
Jaehyeong Jo*, Jinheon Baek*, Seul Lee*, Dongki Kim, Minki Kang and Sung Ju Hwang, NeurIPS 2021

(*: equal contribution)
[paper] 

[C65] Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

Soojung Yang, Doyeong Hwang, Seul Lee, Seongok Ryu and Sung Ju Hwang, NeurIPS 2021
[paper] 

[C64] Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss
Jung Hyun Lee, Jihun Yun, Sung Ju Hwang and Eunho Yang, ICCV 2021
[paper] 

[C63] Multi-domain Knowledge Distillation via Uncertainty-Matching for End-to-End ASR Models
Ho-Gyeong Kim, Min-Joong Lee, Hoshik Lee, Tae Gyoon Kang, Jihyun Lee, Eunho Yang and Sung Ju Hwang, INTERSPEECH 2021
[paper] 

[C62] Adversarial Purification with Score-based Generative Models
Jongmin Yoon, Sung Ju Hwang, Juho Lee, ICML 2021
[paper] 

[C61] Large-Scale Meta-Learning with Continual Trajectory Shifting
Jaewoong Shin, Hae Beom Lee, Boqing Gong, Sung Ju Hwang, ICML 2021
[paper] 

[C60] Learning to Generate Noise for Robustness Against Multiple Perturbations
Divyam Madaan, Jinwoo Shin, Sung Ju Hwang, ICML 2021
[paper] 

[C59] Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

Dongchan Min, Dong Bok Lee, Eunho Yang, Sung Ju Hwang, ICML 2021
[paper] 

[C58] Federated Continual Learning with Weighted Inter-client Transfer
Jaehong Yoon*, Wonyong Jeong*, Giwoong Lee, Eunho Yang, Sung Ju Hwang ICML 2021

(*: equal contribution)
[paper] 

[C57] Learning to Perturb Word Embeddings for Out-of-distribution QA
Seanie Lee, Minki Kang, Juho Lee and Sung Ju Hwang, ACL 2021
[paper] 

[C56] RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung Ju Hwang, Jinwoo Shin, IJCAI 2021 
[paper] 

[C55] Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning
Dong Bok Lee, Dongchan Min, Seanie Lee and Sung Ju Hwang, ICLR 2021 (spotlight)
[paper] 

[C54] Accurate Learning of Graph Representations with Graph Multiset Pooling
Jinheon Baek, Minki Kang and Sung Ju Hwang, ICLR 2021
[paper] 

[C53] Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
Hayeon Lee, Eunyoung Hyung and Sung Ju Hwang, ICLR 2021
[paper] 

[C52] Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
Seanie Lee, Dong Bok Lee and Sung Ju Hwang, ICLR 2021
[paper] 

[C51] Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning
Wonyong Jeong, Jaehong Yoon, Eunho Yang and Sung Ju Hwang, ICLR 2021
[paper] 

[C50] Learning to Sample with Local and Global Contexts from Experience Replay Buffers
Youngmin Oh, Kimin Lee, Jinwoo Shin Eunho Yang and Sung Ju Hwang, ICLR 2021
[paper] 

[C49] FedMix: Approximation of Mixup under Mean Augmented Federated Learning
Tehrim Yoon, Sumin Shin, Sung Ju Hwang and Eunho Yang, ICLR 2021
[paper] 

[C48] Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning
Tuan Nguyen*, Hyewon Jeong*, Eunho Yang and Sung Ju Hwang, AAAI 2021
(*: equal contribution)
[paper] 

[C47] GTA: Graph Truncated Attention for Retrosynthesis
Seung-Woo Seo, You Young Song, June Yong Yang, Seohui Bae, Hankook Lee, Jinwoo Shin, Sung Ju Hwang, and Eunho Yang, AAAI 2021
[paper] 

[C46] Adversarial Self-Supervised Contrastive Learning
Minseon Kim, Jihoon Tack, and Sung Ju Hwang, NeurIPS 2020
[paper] [code]

[C45] Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
Jinheon Baek, Dong Bok Lee, and Sung Ju Hwang, NeurIPS 2020
[paper] [code]

[C44] MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
Jeongun Ryu*, Jaewoong Shin*, Hae Beom Lee*, and Sung Ju Hwang, NeurIPS 2020 (spotlight)

(*:equal contribution)
[paper] 

[C43] Time-Reversal Symmetric ODE Network
In Huh, Eunho Yang, Sung Ju Hwang, and Jinwoo Shin, NeurIPS 2020
[paper] 

[C42] Bootstrapping Neural Processes
Juho Lee, Yoonho Lee, Jungtaek Kim, Eunho Yang, Sung Ju Hwang, and Yee Whye Teh, NeurIPS 2020
[paper] 

[C41] Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning
Youngsung Kim, Jinwoo Shin, Eunho Yang and Sung Ju Hwang, NeurIPS 2020
[paper] 

[C40] Neural Complexity Measures
Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, and Seungjin Choi, NeurIPS 2020
[paper] 

[C39] Attribution Preservation in Network Compression for Reliable Network Interpretation
Geondo Park, June Yong Yang, Sung Ju Hwang, and Eunho Yang, NeurIPS 2020
[paper] 

[C38] Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
Jaehyung Kim, Youngbum Hur, Sejun Park, Eunho Yang, Sung Ju Hwang, and Jinwoo Shin, NeurIPS 2020
[paper] 

[C37] Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation
Minki Kang*, Moonsu Han*, Sung Ju Hwang, EMNLP 2020 (long paper)

(*:equal contribution)
[paper] [bibtex]

[C36] Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
Seong Min Kye, Youngmoon Jung, Hae Beom Lee, Sung Ju Hwang, and Hoirin Kim, INTERSPEECH 2020
[paper] 

[A13] Learning to Sample with Local and Global Contexts in Experience Replay Buffer
Youngmin Oh, Kimin Lee, Jinwoo Shin, Eunho Yang, and Sung Ju Hwang, arXiv:2007.07358, July 2020
[paper] 

[A12] Few-shot Visual Reasoningz with Meta-analogical Contrastive Learning
Youngsung Kim, Jinwoo Shin, Eunho Yang, Sung Ju Hwang, arXiv:2007.12020, July 2020
[paper] 

[W11] Federated Continual Learning with Adaptive Parameter Communication
Jaehong Yoon*, Wonyong Jeong*, Giwoong Lee, Eunho Yang, and Sung Ju Hwang, ICML Workshop on Lifelong Learning 2020 (*: equal contribution)
[paper] 

[A11] Learning to Generate Noise for Robustness against Multiple Perturbations
Divyam Madaan, Jinwoo Shin and Sung Ju Hwang, June 2020
[paper] 

[A10] Transductive Few-shot Learning with Meta-Learned Confidence
Seong Min Kye, Hae Beom Lee, Hoirin Kim, and Sung Ju Hwang, arXiv:2002.12017, June 2020
[paper] 

[A9] Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning
Tuan A. Nguyen*, Hyewon Jeong*, Eunho Yang, and Sung Ju Hwang, arXiv:2006.12777, June 2020​
(*: equal contribution) 
[paper] 

[W12] Federated Semi-Supervised Learning with Inter-Client Consistency
Wonyong Jeong, Jaehong Yoon, Eunho Yang, and Sung Ju Hwang, ICML Workshop on Federated Learning 2020 (Long Presentation) - Best Student Paper Award
[paper] 

[A8] Rapid Structural Pruning of Neural Networks with Set-based Task Adaptive Meta-Pruning
Minyoung Song, Jaehong Yoon, and Sung Ju Hwang, June 2020
[paper] 

[A7] Stochastic Subset Selection
Tuan A. Nguyen*, Bruno Andreis*, Juho Lee, Eunho Yang, and Sung Ju Hwang, June 2020
​(*: equal contribution) 
[paper] 

[C35]  Adversarial Neural Pruning with Latent Vulnerability Suppression 
Divyam Madaan, Jinwoo Shin and Sung Ju Hwang, ICML 2020
[paper]

[C34] Cost-effective Interactive Attention Learning with Neural Attention Process
Jay Heo, Junhyeon Park, Hyewon Jeong, Kwang Joon Kim, Juho Lee, Eunho Yang and Sung Ju Hwang, ICML 2020

[paper]

[C33] Meta Variance Transfer: Learning to Augment from the Others
Seong Jin Park, Seungju Han, Ji-won Baek, Insoo Kim, Juhwan Song, Hae Beom Lee,  Jae-Joon Han and Sung Ju Hwang, ICML 2020

[paper]

[C32] Self-supervised Label Augmentation via Input Transformations
Hankook Lee, Sung Ju Hwang and Jinwoo Shin, ICML 2020
[paper]

[C31] Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs
Dong Bok Lee*, Seanie Lee*, Woo Tae Jeong, Donghwan Kim and Sung Ju Hwang,  ACL 2020 (long paper)

​(*: equal contribution)
[paper][bibtex]

[C30] Segmenting 2K-Videos at 36.5 FPS with 24.3 GFLOPs: Accurate and Lightweight Realtime Semantic Segmentation Networks
Dokwan Oh, Daehyun Ji, Cheolhun Jang, Yoonsuk Hyun, Hong S. Bae and Sung Ju Hwang, ICRA 2020 
[paper]

​

[C29] Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
Hae Beom Lee*, Hayeon Lee*, Donghyun Na*, Saehoon Kim, Minseop Park, Eunho Yang and Sung Ju Hwang, ICLR 2020 (oral presentation)(*: equal contribution) 
[paper] [codes] [bibtex​]

[C28] Meta Dropout: Learning to Perturb Latent Features for Generalization
Hae Beom Lee, Taewook Nam, Eunho Yang and Sung Ju Hwang, ICLR 2020
[paper] [codes] [bibtex​]

[C27] Scalable and Order-robust Continual Learning with Additive Parameter Decomposition
Jaehong Yoon, Saehoon Kim, Eunho Yang and Sung Ju Hwang, ICLR 2020
[paper] [codes] [bibtex​]

[C26]  Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks
Joonyoung Yi, Juhyuk Lee, Sung Ju Hwang and Eunho Yang, ICLR 2020
[paper] [bibtex​]

[C25]  Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare
Ingyo Chung, Saehoon Kim, Juho Lee, Sung Ju Hwang and Eunho Yang, AAAI 2020
[paper] [codes] [bibtex​]

[W10] Adversarial Neural Pruning
Divyam Madaan, Jinwoo Shin and Sung Ju Hwang, NeurIPS  Workshop on Safety and Robustness in Decision Making 2019
[paper]

[W9] Uncertainty-Aware Deep Temporal Asymmetric Multi-task Learning
Hyewon Jeong, Tuan Anh Nguyen, Eunho Yang and Sung Ju Hwang, NeurIPS Women in Machine Learning Workshop 2019

[A6] Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bit-wise Regularization
Jihun Yun, Jung Hyun Lee, Sung Ju Hwang and Eunho Yang, arXiv:1911.12990, Nov 2019
[paper] 

[A5] Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection
Byunggill Joe, Sung Ju Hwang and Insik Shin, arXiv:1909.04311, Sep 2019
[paper] 

[W8]  Interactive Attention Learning for Action Recognition
Jay Heo, Junhyeon Park, Hyewon Jeong, Wuhyun Shin, Kwang Joon Kim, and Sung Ju Hwang, 
ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models 2019

[A4] Reliable Estimation of Individual Treatment Effect with Causal Information Bottleneck

Sungyub Kim, Yongsu Baek, Sung Ju Hwang and Eunho Yang, arXiv:1906.03118, Jun 2019
[paper]

[C24]  Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data
Moonsu Han*, Minki Kang*, Hyunwoo Jung, Sung Ju Hwang, ACL 2019 (long paper) (oral presentation) 
(*: equal contribution)
[paper] [codes] [bibtex​]

[C23] Learning What and Where to Transfer
Yunhun Jang, Hankook Lee, Sung Ju Hwang, and Jinwoo Shin, ICML 2019
[paper] [codes] [bibtex​]

[C22] Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss
Sangil Jung, Changyong Son, Seohyung Lee, Jinwoo Son, Jae-Joon Han, Youngjun Kwak, Sung Ju Hwang and Changkyu Choi, CVPR 2019 (oral presentation)
[paper] [bibtex​]

[C21] Learning to Propagate Labels: Transductive Propagation Networks for Few-shot Learning
Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang and Yi Yang, ICLR 2019
[paper] [codes] [bibtex​]

[A3] Learning to Separate Domains in Generalized Zero-Shot and Open Set Learning: a probabilistic perspective
Hanze Dong, Yanwei Fu, Leonid Sigal, Sung Ju Hwang, Yu-Gang Jiang and Xiangyang Xue, arXiv:1810.07368, Nov 2018
[paper]

[C20] DropMax: Adaptive Variational Softmax
Haebeom Lee, Juho Lee, Saehoon Kim, Eunho Yang and Sung Ju Hwang, NeurIPS 2018
[paper] [codes] [bibtex​]

[C19] Uncertainty-Aware Attention for Reliable Interpretation and Prediction
Jay Heo*, Haebeom Lee*, Saehoon Kim, Juho Lee, Kwangjun Kim, Eunho Yang, and Sung Ju Hwang, NeurIPS 2018 (*: equal contribution)
[paper] [codes] [bibtex​]

[C18] Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding
Hajin Shim, Sung Ju Hwang and Eunho Yang, NeurIPS 2018
[paper] [codes] [bibtex​]

[A2] Adaptive Network Sparsification with Dependent Beta-Bernoulli Dropout
Juho Lee, Saehoon Kim, Haebeom Lee, Jaehong Yoon, Eunho Yang, and Sung Ju Hwang, arXiv:1805.10896, May 2018
[paper]

[C17] Deep Asymmetric Multi-task Feature Learning
Haebeom Lee, Eunho Yang and Sung Ju Hwang, ICML 2018
[paper] [codes] [bibtex]

[C16] Lifelong Learning with Dynamically Expandable Networks
Jaehong Yoon, Eunho Yang, Jeongtae Lee, and Sung Ju Hwang, ICLR 2018

[paper] [codes] [bibtex]

[C15] SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization
Juyong Kim, Yookoon Park, Gunhee Kim and Sung Ju Hwang, ICML 2017
[paper] [codes] [bibtex]

[C14] Combined Group and Exclusive Sparsity for Deep Neural Networks
Jaehong Yoon and Sung Ju Hwang, ICML 2017
[paper] [codes] [bibtex]

[C13] Taxonomy-Regularized Semantic Deep Convolutional Neural Networks
Wonjoon Goo, Juyong Kim, Gunhee Kim and Sung Ju Hwang, ECCV 2016

[paper] [codes] [bibtex]

[C12] Asymmetric Multi-task Learning Based on Task Relatedness and Loss
Giwoong Lee, Eunho Yang and Sung Ju Hwang, ICML 2016
[paper] [codes] [bibtex]

[C11] Knowledge Transfer with Interactive Learning of Semantic Relationships
Jonghyun Choi, Sung Ju Hwang, Leonid Sigal, and Larry S. Davis, AAAI 2016 (oral presentation)
[paper] [bibtex]

[C10] Exploiting View-Specific Appearance Similarities Across Classes for Zero-shot Pose Prediction: A Metric Learning Approach
Alina Kuznetsova, Sung Ju Hwang, Bodo Rosenhahn, and Leonid Sigal, AAAI 2016
[paper] [bibtex]

[C9] Expanding Object Detector’s Horizon: Incremental Learning Framework for Object Detection in Videos
Alina Kuznetsova, Sung Ju Hwang, Bodo Rosenhahn, and Leonid Sigal, CVPR 2015
[paper] [bibtex]

[W6] A Metric Learning Approach for Multi-View Object Recognition and Zero-shot Pose Estimation
Alina Kuznetsova, Sung Ju Hwang, Bodo Rosenhahn and Leonid Sigal, ICCV Workshop on Object Understanding for Interaction 2015
[paper]

[W5] Interactive Semantics for Knowledge Transfer
Jonghyun Choi, Sung Ju Hwang, Leonid Sigal and Larry S. Davis, ICML Active Learning Workshop 2015
[paper]

[W4] A Unified Semantic Embedding: Relating Taxonomies and Attributes
Sung Ju Hwang and Leonid Sigal, AAAI  Spring Symposium on Knowledge Representation and Reasoning (KRR) 2015
[paper]

[A1] Hierarchical Maximum-Margin Clustering
Guang-Tong Zhou, Sung Ju Hwang, Mark Schmidt, Leonid Sigal and Greg Mori, arXiv:1502.01827, Feb 2015
[paper]

[W3] A Unified Semantic Embedding: Relating Taxonomies and Attributes

Sung Ju Hwang and Leonid Sigal, NIPS Workshop on Learning Semantics 2014
[paper]

[C8] A Unified Semantic Embedding: Relating Taxonomies with Attributes
Sung Ju Hwang and Leonid Sigal, NIPS 2014
[paper] [bibtex]

[C7] Analogy-preserving Semantic Embedding for Visual Object Categorization
Sung Ju Hwang, Kristen Grauman and Fei Sha, ICML 2013
[paper] [bibtex]

[J2] Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search 
Sung Ju Hwang and Kristen Grauman, International Journal of Computer Vision (IJCV), November 2012
[paper] [codes&data]

[J1] Reading Between the Lines: Object Localization Using Implicit Cues from Image Tags
Sung Ju Hwang and Kristen Grauman, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), June 2012
[paper]

[W2] Semantic Kernel Forests from Multiple Taxonomies
Sung Ju Hwang, Fei Sha and Kristen Grauman, NIPS Big Data Meets Computer Vision: International Workshop on Large Scale Visual Recognition and Retrieval (BigVision) 2012 (oral presentation)
[paper]

[C6] Semantic Kernel Forests from Multiple Taxonomies
Sung Ju Hwang, Kristen Grauman and Fei Sha, NIPS 2012
[paper] [bibtex]

[C5] Context-Based Automatic Local Image Enhancement

Sung Ju Hwang, Ashish Kapoor, and Sing Bing Kang, ECCV 2012

[paper] [bibtex]

[C4] Learning a Tree of Metrics with Disjoint Visual Features
Sung Ju Hwang, Kristen Grauman, and Fei Sha, NIPS 2011
[paper] [codes]​ [bibtex]

[W1] Sharing Features Between Visual Tasks at Different Levels of Granularity
Sung Ju Hwang, Fei Sha and Kristen Grauman, CVPR Fine-Grained Visual Categorization Workshop (FGVC) 2011
[paper]

[C3] Sharing Features Between Objects and Their Attributes
Sung Ju Hwang, Fei Sha and Kristen Grauman, CVPR 2011
[paper] [bibtex]

[C2] Accounting for the Relative Importance of Objects in Image Retrieval

Sung Ju Hwang and Kristen Grauman, BMVC 2010 (oral presentation)
[paper] [codes&data] [bibtex]

[C1] Reading Between The Lines: Object Localization Using Implicit Cues from Image Tags
Sung Ju Hwang and Kristen Grauman, CVPR 2010 (oral presentation)
[paper] [bibtex]