Conducting
state-of-the-art research

Conducting
state-of-the-art research

Conducting
state-of-the-art research

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

Jaewoo Lee, Jaehong Yoon, Wonjae Kim, YunJi Kim and Sung Ju Hwang

ICML 2024

Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

Jaehyeong Jo and Sung Ju Hwang

ICML 2024

Graph Generation with Diffusion Mixture

Jaehyeong Jo, Dongki Kim and and Sung Ju Hwang

ICML 2024

Drug Discovery with Dynamic Goal-aware Fragments

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

ICML 2024

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

Daeun Lee, Jaehong Yoon and Sung Ju Hwang

ICML 2024

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

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

ICML 2024

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

Adaptive-RAG: Learning to Adapt Retreival-Augmented Large Language Models through Question complexity

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

NAACL 2024

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

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

Beomgyoung Kim, Joonsang Yu and Sung Ju Hwang

CVPR 2024

SEA: Sparse Linear Attention with Estimated Attention Mask

HeeJun Lee, Jina Kim, Jeffrey Willette, Sung Ju Hwang

ICLR 2024

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

Sohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, and Sung Ju Hwang

ICLR 2024

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

Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations

Hyeonjeong Ha, Minseon Kim and Sung Ju Hwang

NeurIPS 2023

Effective Targeted Attacks for Adversarial Self-Supervised Learning

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

NeurIPS 2023

Language Detoxification with Attribute-Discriminative Latent Space

Jinmyung Kwak, Minseon Kim, and Sung Ju Hwang

ACL 2023

Sparse Token Transformers with Attention Back Tracking

Heejun Lee, Minki Kang, Youngwan Lee and Sung Ju Hwang

ICLR 2023

Identity decoupling for multi-subject personalization of text-to-image models

Sangwon Jang, Jaehyeong Jo, Kimin Lee and Sung Ju Hwang

NeursIPS 2024

Set-based Neural Network encoding without weight tying

Bruno Andresis, Soro Bedionita, Phillip Torr and Sung Ju Hwang

NeurIPS 2024

Latent Paraphrasing : Perturbation on layers improves knowledge injection in language models

Minki Kang, Gibbeum Lee, Jaewoong Cho and Sung Ju Hwang

NeursIPS 2024

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

Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan and Sung Ju Hwang

NAACL 2025

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 and Sung Ju Hwang

ICLR 2025

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 and Sung Ju Hwang

ICLR 2025

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

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

ICLR 2025

Training Free Exponential Context Extension via Cascading KV Cache

Jeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon and Sung Ju Hwang

ICLR 2025

Diffusion-based Neural Network Weights Generation

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

ICLR 2025

KOALA: Empirical lessons toward memory-efficient and fast diffusion models for text-to-image synthesis

Youngwan Lee, Kwanyong Park, Yoorim cho, Yong-Ju Lee and Sung Ju Hwang

NeurIPS 2024

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

Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan and Sung Ju Hwang

Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan and Sung Ju Hwang

NAACL 2025

NAACL 2025

A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
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 and Sung Ju Hwang

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

ICLR 2025

ICLR 2025

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
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 and Sung Ju Hwang

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

ICLR 2025

ICLR 2025

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

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

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

ICLR 2025

ICLR 2025

Training Free Exponential Context Extension via Cascading KV Cache
Training Free Exponential Context Extension via Cascading KV Cache

Jeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon and Sung Ju Hwang

Jeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon and Sung Ju Hwang

ICLR 2025

ICLR 2025

Diffusion-based Neural Network Weights Generation
Diffusion-based Neural Network Weights Generation

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

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

ICLR 2025

ICLR 2025

KOALA: Empirical lessons toward memory-efficient and fast diffusion models for text-to-image synthesis
KOALA: Empirical lessons toward memory-efficient and fast diffusion models for text-to-image synthesis

Youngwan Lee, Kwanyong Park, Yoorim cho, Yong-Ju Lee and Sung Ju Hwang

Youngwan Lee, Kwanyong Park, Yoorim cho, Yong-Ju Lee and Sung Ju Hwang

NeurIPS 2024

NeurIPS 2024

Set-based Neural Network Encoding Without Weight Tying
Set-based Neural Network Encoding Without Weight Tying

Bruno Andreis, Soro Bedionita, Philip Torr and Sung Ju Hwang

Bruno Andreis, Soro Bedionita, Philip Torr and Sung Ju Hwang

NeurIPS 2024

NeurIPS 2024

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

Sangwon Jang, Jaehyeong Jo, Kimin Lee and Sung Ju Hwang

Sangwon Jang, Jaehyeong Jo, Kimin Lee and Sung Ju Hwang

NeurIPS 2024

NeurIPS 2024

Latent Paraphrasing : Perturbation on layers improves knowledge injection in language models
Latent Paraphrasing : Perturbation on layers improves knowledge injection in language models

Minki Kang, Gibbeum Lee, Jaewoong Cho and Sung Ju Hwang

Minki Kang, Gibbeum Lee, Jaewoong Cho and Sung Ju Hwang

NeurIPS 2024

NeurIPS 2024

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

Jaewoo Lee, Jaehong Yoon, Wonjae Kim, YunJi Kim and Sung Ju Hwang

Jaewoo Lee, Jaehong Yoon, Wonjae Kim, YunJi Kim and Sung Ju Hwang

ICML 2024

ICML 2024

Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes
Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

Jaehyeong Jo and Sung Ju Hwang

Jaehyeong Jo and Sung Ju Hwang

ICML 2024

ICML 2024

Graph Generation with Diffusion Mixture
Graph Generation with Diffusion Mixture

Jaehyeong Jo, Dongki Kim and and Sung Ju Hwang

Jaehyeong Jo, Dongki Kim and and Sung Ju Hwang

ICML 2024

ICML 2024

Drug Discovery with Dynamic Goal-aware Fragments
Drug Discovery with Dynamic Goal-aware Fragments

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

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

ICML 2024

ICML 2024

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

Daeun Lee, Jaehong Yoon and Sung Ju Hwang

Daeun Lee, Jaehong Yoon and Sung Ju Hwang

ICML 2024

ICML 2024

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

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

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

ICML 2024

ICML 2024

One Prompt is not Enough: Automated Construction off a Mixture-of-Experts Prompts
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,

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

ICML 2024

ICML 2024

Adaptive-RAG: Learning to Adapt Retreival-Augmented Large Language Models through Question complexity
Adaptive-RAG: Learning to Adapt Retreival-Augmented Large Language Models through Question complexity

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

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

NAACL 2024

NAACL 2024

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

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

NAACL 2024

NAACL 2024

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

Beomgyoung Kim, Joonsang Yu and Sung Ju Hwang

Beomgyoung Kim, Joonsang Yu and Sung Ju Hwang

CVPR 2024

CVPR 2024

SEA: Sparse Linear Attention with Estimated Attention Mask
SEA: Sparse Linear Attention with Estimated Attention Mask

HeeJun Lee, Jina Kim, Jeffrey Willette, Sung Ju Hwang

HeeJun Lee, Jina Kim, Jeffrey Willette, Sung Ju Hwang

ICLR 2024

ICLR 2024

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

Sohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, and Sung Ju Hwang

Sohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, and Sung Ju Hwang

ICLR 2024

ICLR 2024

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

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

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

NeurIPS 2023

NeurIPS 2023

Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations

Hyeonjeong Ha, Minseon Kim and Sung Ju Hwang

Hyeonjeong Ha, Minseon Kim and Sung Ju Hwang

NeurIPS 2023

NeurIPS 2023

Effective Targeted Attacks for Adversarial Self-Supervised Learning
Effective Targeted Attacks for Adversarial Self-Supervised Learning

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

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

NeurIPS 2023

NeurIPS 2023

Language Detoxification with Attribute-Discriminative Latent Space
Language Detoxification with Attribute-Discriminative Latent Space

Jinmyung Kwak, Minseon Kim, and Sung Ju Hwang

Jinmyung Kwak, Minseon Kim, and Sung Ju Hwang

ACL 2023

ACL 2023

Sparse Token Transformers with Attention Back Tracking
Sparse Token Transformers with Attention Back Tracking

Heejun Lee, Minki Kang, Youngwan Lee and Sung Ju Hwang

Heejun Lee, Minki Kang, Youngwan Lee and Sung Ju Hwang

ICLR 2023

ICLR 2023

Products

Technology

Publication

Company

Blog

Privacy Policy

Terms of Service

Email

Naver D2 Startup Campus, Seoul, 06620 South Korea 🇰🇷

8 The Green 14844 Dover DE 19901, USA 🇺🇸

© DeepAuto.ai All rights reserved. Privacy Policy.

Products

Technology

Publication

Company

Blog

Privacy Policy

Terms of Service

Email

Naver D2 Startup Campus, Seoul, 06620 South Korea 🇰🇷

8 The Green 14844 Dover DE 19901, USA 🇺🇸

© DeepAuto.ai All rights reserved. Privacy Policy.

Products

Technology

Publication

Company

Blog

Privacy Policy

Terms of Service

Home

Email

Naver D2 Startup Campus, Seoul, 06620 South Korea 🇰🇷

8 The Green 14844 Dover DE 19901, USA 🇺🇸

© DeepAuto.ai All rights reserved. Privacy Policy.