AI 우수학술대회 논문_2025

AI 우수학술대회 논문

전체

2025

2024

2023

2022

2021

2020

2026

Ghosted layers: Unconstrained activation alignment for recovering layer-pruned LLMs
Daniel Yun, Junhyuk Jo, Sai Praneeth Karimireddy and Sunwoo Lee, Proc. Neural Information Processing Systems (NeurIPS 2026), 2026
Patch rebirth: Fast and transferable model inversion of vision transformers
Seongsoo Heo and Dong-Wan Choi, Proc. Neural Information Processing Systems (NeurIPS 2026), 2026
A transformer architecture via lightweight sigmoid attention for graph collaborative filtering
Hyungjin Kim, Seokho Ahn, Minhye Jeon, Sungbok Shin and Young-Duk Seo, Proc. International ACM Conference on Information and Knowledge Management (CIKM 2026), 2026
Locality-aware redundancy pruning for LLM depth compression
Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo, Minkyu Kim and Sunwoo Lee, Proc. Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), 2026
DiffuFlicker: Diffusion-based LED traffic light flicker removal in dashcam videos
Sujin Kim, Juwon Lee and In Kyu Park, Proc. International Conference on Pattern Recognition (ICPR 2026), 2026 DOI
Geometry-correct diffusion posterior sampling with denoiser-pullback curvature guidance and manifold-aligned damping
Seunghyeok Shin, Minwoo Kim, Dabin Kim and Hongki Lim, Proc. International Conference on Machine Learning (ICML 2026), 2026
Towards robust vision transformers: Path dependency analysis and a simple two-stage adversarial training
Seongmin Kim and Byung Cheol Song, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026), 2026
FAST‑DIPS: Adjoint‑free analytic steps and hard‑constrained likelihood correction for diffusion‑prior inverse problems
Minwoo Kim, Seunghyeok Shin and Hongki Lim, Proc. International Conference on Learning Representations (ICLR 2026), 2026
A compliance-preserving retrieval system for aircraft MRO task search
Byungho Jo, Proc. European Chapter of the Association for Computational Linguistics (EACL 2026), 2026
HE-DAP: Homomorphic encryption-based dynamic adaptive parameter optimization for statistical computation
Yun-Soo Park, Hyunmin Choi, Hyoungshick Kim and Mun-Kyu Lee, Proc. of The 41st ACM/SIGAPP Symposium On Applied Computing (SAC 2026), 2026 DOI
T2LF: LLM-guided multimodal diffusion for text-to-light field synthesis
Soyoung Yoon, Namhyuk Ahn and In Kyu Park, Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026 / Best Paper Award Finalist; 13/832 ≈ 1.6%), 2026 DOI
GEM: A scale-aware and distribution-sensitive sparse fine-tuning framework for effective downstream adaptation
Sungmin Kang, Jisoo Kim, Salman Avestimehr and Sunwoo Lee, Proc. Annual AAAI Conference on Artificial Intelligence (AAAI 2026), 2026

2025

Layer-wise update aggregation with recycling for communication-efficient federated learning
Jisoo Kim, Sungmin Kang, Sunwoo Lee, Proc. Neural Information Processing Systems (NeurIPS 2025), 2025 DOI
LAFUL: Lesion-aware federated unlearning via channel-wise gradient masking and feature distillation
Qingyu Tan, Yan Li and Byeong-Seok Shin, Proc. IEEE Conference on Bioinformatics and Biomedicine (BIBM 2025), 2025
Adaptive 3D reconstruction via diffusion priors and forward curvature-matching likelihood updates
Seunghyeok Shin, Dabin Kim and Hongki Lim, Proc. Neural Information Processing Systems (NeurIPS 2025), 2025
FaceGCD: Generalized face discovery via dynamic prefix generation
Yunseok Oh and Dong-Wan Choi, Proc. British Machine Vision Conference (BMVC 2025), 2025 DOI
Lossless token merging even without fine-tuning in vision transformers
Jaeyeon Lee and Dong-Wan Choi, European Conference on Artificial Intelligence (ECAI 2025), 2025 DOI
Draw your mind: Personalized generation via condition-level modeling in text-to-image diffusion models
Hyungjin Kim, Seokho Ahn and Young-Duk Seo, Proc. IEEE/CVF International Conference on Computer Vision (ICCV 2025), 2025 논문 보기
M2SFormer: Multi-spectral and multi-scale attention with edge-aware difficulty guidance for image forgery localization
Ju-Hyeon Nam, Dong-Hyun Moon and Sang-Chul Lee, Proc. IEEE/CVF International Conference on Computer Vision (ICCV 2025), 2025
A plug-and-play approach for robust image editing in text-to-image diffusion models
Hyunwook Jo, Jiseung Maeng, Jun Hyung Park, Namhyuk Ahn and In Kyu Park, Proc. IEEE/CVF International Conference on Computer Vision Workshop (ICCVW 2025), 2025
Parecon: Enhancing mobile AI vision apps through DNN partition and resolution control
Junsoo Park and Yeongjin Kim, Proc. International Conference on Mobile Ad-Hoc and Smart Systems (MASS 2025), 2025 DOI
BounDr.E: Predicting drug-likeness via biomedical knowledge alignment and EM-like one-class boundary optimization
Dongmin Bang, Inyoung Sung, Yinhua Piao, Sangseon Lee and Sun Kim, Proc. International Conference on Machine Learning (ICML 2025), 2025 논문 보기
Nearly zero-cost protection against mimicry by personalized diffusion models
Namhyuk Ahn et al., Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), 2025 논문 보기
Two is better than one: Efficient ensemble defense for robust and compact models
Yoojin Jung and Byung Cheol Song, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), 2025 논문 보기
Link to the past: Temporal propagation for fast 3D human reconstruction from monocular video
Matthew Marchellus, Nadhira Noor and In Kyu Park, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), 2025 논문 보기
CheapNet: Cross-attention on hierarchical representations for efficient protein-ligand binding affinity prediction
Hyukjoon Lim, Sun Kim, Sangseon Lee, The Thirteenth International Conference on Learning Representations (ICLR 2025), 2025 논문 보기
Overlapped bootstrapping for FHEW/TFHE and its application to SHA3
Deokhwa Hong, Youngjin Choi, Yongwoo Lee and Young-Sik Kim, Proc. Financial Cryptography and Data Security (FC) 2025 (FC 2025), 2025 DOI
UKTA: Unified Korean text analyzer
Seokho Ahn, Junhyung Park, Ganghee Go, Chulhui Kim, Jiho Jung, Myung Sun Shin, Do-Guk Kim, Young-Duk Seo, Proc. ACM/SIGAPP Symposium On Applied Computing (SAC 2025), 2025 DOI
Topic-aware knowledge graph with large language models for interoperability in recommender systems
Minhye Jeon, Seokho Ahn, Young-Duk Seo, Proc. ACM/SIGAPP Symposium On Applied Computing (SAC 2025), 2025 DOI
Real-time calibration model for low-cost sensor in fine-grained time series
Seokho Ahn , Hyungjin Kim , Sungbok Shin and Young-Duk Seo, Proc. AAAI Conference on Artificial Intelligence (AAAI 2025), 2025 DOI

2024

A new multi-source light detection benchmark and semi-supervised focal light detection
Jae-Yong Baek, Yong-Sang Yoo and Seung-Hwan Bae, Proc. Neural Information Processing Systems (NeurIPS 2024), 2024 논문 보기
Detecting concept shifts under different levels of self-awareness on emotion labeling
HyoSeon Choi, Dahoon Choi, Netiwit Kaongeon and Byung Hyung Kim, Proc. International Conference on Pattern Recognition (ICPR 2024), 2024 DOI
Cascading global and sequential temporal representations with local context modeling for EEG-based emotion recognition
Hyunwook Kang, Jin Woo Choi and Byung Hyung Kim, Proc. International Conference on Pattern Recognition (ICPR 2024), 2024 DOI
Deterministic synthesis of defect images using null optimization
Hyunwook Jo Marcellino Sahadewa, William Gazali and In Kyu Park, Proc. International Conference on Pattern Recognition (ICPR 2024), 2024 DOI
Geometrically consistent light field synthesis using repaint video diffusion model
Soyoung Yoon and In Kyu Park, Proc. International Conference on Pattern Recognition (ICPR 2024), 2024 DOI
Attention-guided energy-based model for out-of-distribution data detection
Zongjing Cao, Yan Li and Byeong-Seok Shin, Proc. International Conference on Pattern Recognition (ICPR 2024), 2024 DOI
Embracing domain gradient conflicts: Domain generalization using domain gradient equilibrium
Zuyu Zhang, Yan Li and Byeong-Seok Shin, Proc. ACM Multimedia Conference (ACM MM 2024), 2024 DOI
VizECGNet: Visual ECG image network for cardiovascular diseases classification with multi-modal training and knowledge distillation
Ju-Hyeon Nam, Seo-Hyeong Park, Su Jung Kim, and Sang-Chul Lee, Proc. International Conference on Image Processing (ICIP 2024), 2024 DOI
COVID19 to pneumonia: Multi region lung severity classification using CNN transformer position-aware feature encoding network
Jongbub Lee, Jungsoo Kim and Hyungyu Lee, Proc. International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2024), 2024 DOI
All you need is your voice: Emotional face representation with audio perspective for emotional talking face generation
Seongho Kim and Byung Cheol Song, Proc. European Conference on Computer Vision (ECCV 2024), 2024 DOI
Proactive content caching via interplay between deep learning and stochastic optimization
Yongmoon Park, Kyungtae Lee, Minseok Choi and Yeongjin Kim, Proc. International Conference on Mobile Ad-Hoc and Smart Systems (MASS 2024), 2024 DOI
Layer-wise adaptive gradient norm penalizing method for efficient and accurate deep learning
Sunwoo Lee, Proc. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024), 2024 DOI
Modality-agnostic domain generalizable medical image segmentation by multi-frequency in multi-scale attention
Ju-Hyeon Nam, Nur Suriza Syazwany, Su Jung Kim and Sang-Chul Lee, Proc. Computer Vision and Pattern Recognition (CVPR 2024), 2024 DOI
Efficient skeleton-based action recognition for real-time embedded systems
Nadhira Noor, Fabianaugie Jametoni, Jinbeom Kim, Hyunsu Hong and In Kyu Park, Proc. CVPR Workshop on Mobile AI (CVPRW 2024), 2024 DOI
RecKG: Knowledge graph for recommender systems
Junhyuk Kwon, Seokho Ahn and Young-Duk Seo, Proc. ACM/SIGAPP Symposium on Applied Computing (SAC 2024), 2024 DOI
Recall-oriented continual learning with generative adversarial meta-model
Haneol Kang and Dong-Wan Choi, Proc. AAAI Conference on Artificial Intelligence (AAAI 2024), 2024 DOI
Teacher as a lenient expert: Teacher-agnostic data-free knowledge distillation
Hyunjune Shin, and Dong-Wan Choi, Proc. AAAI Conference on Artificial Intelligence (AAAI 2024), 2024 DOI

2023

Modality-aware OOD suppression using feature discrepancy for multi-modal emotion recognition
Dohee Kang, Somang Kang, Daeha Kim and Byung Cheol Song, Proc. International Conference on Image Processing (ICIP 2023), 2023 DOI
EGformer: Equirectangular geometry-biased transformer for 360 depth estimation
Ilwi Yun, Chanyong Shin, Hyunku Lee, Hyuk-Jae Lee and Chae Eun Rhee, Proc. International Conference on Computer Vision (ICCV 2023), 2023 DOI
M2C: Concise music representation for 3D dance generation
Matthew Marchellus and In Kyu Park, Proc. ICCV Workshop on Analysis and Modeling of Faces and Gestures (ICCVW 2023), 2023 DOI
Dynamic interplay between service caching and code offloading in mobile-edge-cloud networks
Dongho Ham, Yeongjin Kim and Jeongho Kwak, Proc. International Conference on Sensing, Communication, and Networking (SECON 2023), 2023 DOI
Hetal: Efficient privacy-preserving transfer learning with homomorphic encryption
Seewoo Lee, Garam Lee, Jung Woo Kim, Junbum Shin and Mun-Kyu Lee, Proc. International Conference on Machine Learning (ICML 2023), 2023 논문 보기
Light field synthesis from a monocular image using variable LDI
Junhyeong Bak and In Kyu Park, Proc. CVPR Workshop on Light Field for Computer Vision (CVPRW 2023), 2023 DOI
Relation modeling on knowledge graph for interoperability in recommender systems
SeungJoo Lee, Seokho Ahn and Young-Duk Seo, Proc. Symposium on Applied Computing (SAC 2023), 2023 DOI
Better generalized few-shot learning even without base data
Seong-Woong Kim and Dong-Wan Choi, Proc. AAAI Conference on Artificial Intelligence (AAAI 2023), 2023 DOI
Semantic-aware superpixel for weakly supervised semantic segmentation
Sangtae Kim, Daeyoung Park and Byonghyo Shim, Proc. AAAI Conference on Artificial Intelligence (AAAI 2023), 2023 DOI
Fine gaze redirection learning with gaze hardness-aware transformation
Sangjin Park, Daeha Kim and Byung Cheol Song, Proc. Winter Conference on Applications of Computer Vision (WACV 2023), 2023 DOI
IFQA: Interpretable face quality assessment
Byungho Jo, Donghyeon Cho, In Kyu Park and Sungeun Hong, Proc. Winter Conference on Applications of Computer Vision (WACV 2023), 2023 DOI

2022

Local feature extraction from salient regions by feature map transformation
Yerim Jung, Suriza Syazwany and Sang-Chul Lee, Proc. British Machine Vision Conference (BMVC 2022), 2022 논문 보기
Optimal transport-based identity matching for identity-invariant facial expression recognition
Daeha Kim and Byung Cheol Song, Proc. Neural Information Processing Systems (NeruIPS 2022), 2022 논문 보기
Ensemble knowledge guided sub-network search and fine-tuning for filter pruning
Seunghyun Lee and Byung Cheol Song, Proc. European Conference on Computer Vision (ECCV 2022), 2022 DOI
Emotion-aware multi-view contrastive learning for facial emotion recognition
Daeha Kim and Byung Cheol Song, Proc. European Conference on Computer Vision (ECCV 2022), 2022 DOI
Image enhancement for improved visibility of digital displays under the sunlight
Heejin Lee, Junmin Lee, Seha Jeong, Seunghyun Lee, Seungwan Yu, Junho Heo and Byung Cheol Song, Proc. International Conference on Image Processing (ICIP 2022), 2022 DOI
RPFNET: Complementary feature fusion for hand gesture recognition
Do Yeon Kim, Dae Ha Kim and Byung Cheol Song, Proc. International Conference on Image Processing (ICIP 2022), 2022 DOI
Style transfer using optimal transport via Wasserstein distance
OSeok Ryu and Bowon Lee, Proc. International Conference on Image Processing (ICIP 2022), 2022 DOI
3D body reconstruction revisited: Exploring the test-time 3D body mesh refinement strategy via surrogate adaptation
Jonathan Samuel Lumentut and In Kyu Park, Proc. ACM International Conference on Multimedia (ACM MM 2022), 2022 DOI
Re-ordered micro image based high efficient residual coding in light field compression
Hyunmin Jung, Hyuk-Jae Lee and Chae Eun Rhee, Proc. ACM International Conference on Multimedia (ACM MM 2022), 2022 DOI
Phase vocoder for time stretch based on center frequency estimation
Donghyeon Kim and Bowon Lee, Proc. Interspeech (Interspeech 2022), 2022 DOI
Deformable part region learning for object detection
Seung-Hwan Bae, Proc. AAAI Conference on Artificial Intelligence (AAAI 2022), 2022 DOI
Style-guided and disentangled representation for robust image-to-image translation
Jaewoong Choi, Dae Ha Kim and Byung Cheol Song, Proc. AAAI Conference on Artificial Intelligence (AAAI 2022), 2022 DOI
Contextual gradient scaling for few-shot learning
Sanghyuk Lee, Seunghyun Lee and Byung Cheol Song, Proc. Winter Conference on Applications of Computer Vision (WACV 2022), 2022 DOI