2025
[PACT] SPipe: Hybrid GPU and CPU Pipeline for Training LLMs under Memory Pressure
Proceedings of the 34th ACM/IEEE/IFIP International Conference on Parallel Architectures and Compilation Techniques, Irvine, California, USA, November, 2025
[ICCV] UDC-VIT: A Real-World Video Dataset for Under-Display Cameras
Proceedings of the 21st IEEE/CVF International Conference on Computer Vision, Honolulu, Hawai'i, October, 2025
🏅Spotlight Paper
Link
[ISMIR] Joint Object Detection and Sound Source Separation
Proceedings of the 26th International Society for Music Information Retrieval Conference, Daejeon, South Korea, September, 2025
[ACL] BridG MT: Enhancing LLMs' Machine Translation Capabilities with Sentence Bridging and Gradual MT
Findings of the 63rd annual meeting of the Association for Computational Linguistics, Vienna, Austria, July, 2025
DOI: 10.48550/arXiv.2410.11693
[ACL] Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks
Proceedings of the 63rd annual meeting of the Association for Computational Linguistics, Vienna, Austria, July, 2025
DOI: 10.48550/arXiv.2503.10695
[HPDC] HYPERF: End-to-End Autotuning Framework for High-Performance Computing
Proceedings of the 34th ACM International Symposium on High-Performance Parallel and Distributed Computing, Notre Dame, IN, USA, July, 2025
[ICML] Combinatorial Reinforcement Learning with Preference Feedback
Proceedings of the 42nd International Conference on Machine Learning, Vancouver, BC, Canada, July, 2025
DOI: 10.48550/arXiv.2502.10158
[ICML] Improved Online Confidence Bounds for Multinomial Logistic Bandits
Proceedings of the 42nd International Conference on Machine Learning, Vancouver, BC, Canada, July, 2025
DOI: 10.48550/arXiv.2502.10020
[ICML] Linear Bandits with Partially Observable Features
Proceedings of the 42nd International Conference on Machine Learning, Vancouver, BC, Canada, July, 2025
DOI: 10.48550/arXiv.2502.06142
[ICML] Optimal and Practical Batched Linear Bandit Algorithm
Proceedings of the 42nd International Conference on Machine Learning, Vancouver, BC, Canada, July, 2025
Link
[ICML] Symmetry-Aware GFlowNets
Proceedings of the 42nd International Conference on Machine Learning, Vancouver, BC, Canada, July, 2025
DOI: 10.48550/arXiv.2506.02685
[SIGIR] Graph Spectral Filtering with Chebyshev Interpolation for Recommendation
Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Padua, Italy, July, 2025
DOI: 10.48550/arXiv.2505.00552
[COLT] Experimental Design for Semiparametric Bandits
Proceedings of the 38th annual conference on Learning theory, Lyon, France, June, 2025
DOI: 10.48550/arXiv.2506.13390
[CVPR] Towards Scalable Human-aligned Benchmark for Text-guided Image Editing
Proceedings of the 41st IEEE Conference on Computer Vision and Pattern Recognition, pp. 18292-18301, Nashville, Tennessee, USA, June, 2025
DOI: 10.48550/arXiv.2505.00502
[ESWA] ColonOOD: A Complete Pipeline for Optical Diagnosis of Colorectal Polyps Integrating Out-of-Distribution Detection and Uncertainty Quantification
Expert Systems with Applications, June, 2025
DOI: 10.1016/j.eswa.2025.128756
[ICS] SnuSOLVER: Optimizing Sparse Direct Solvers for Heterogeneous Systems
Proceedings of the 39th ACM International Conference on Supercomputing, Salt Lake City, USA, June, 2025
DOI: 10.1145/3721145.3734531
[ISCA] ATiM: Autotuning Tensor Programs for Processing-in-DRAM
Proceedings of the 52nd Annual International Symposium on Computer Architecture, pages 899-915, Tokyo, Japan, June, 2025
DOI: 10.1145/3695053.3731096
[PAKDD] Mixture of Conditional Attention for Multimodal Fusion in Sequential Recommendation
Proceedings of the 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 278–290, Sydney, Australia, June, 2025
DOI: 10.1007/978-981-96-8180-8_22
[PAKDD] ReducedGCN: Learning to Adapt Graph Convolution for Top-N Recommendation
Proceedings of the 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 291–303, Sydney, Australia, June, 2025
DOI: 10.1007/978-981-96-8180-8_23
[SID] Enhancing Face Recognition Accuracy for Under-Display Cameras via Image Restoration
SID Symposium Digest of Technical Papers, San Jose, USA, June, 2025
🏅Distinguished Paper
[CVPR] PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization
Proceedings of the 41st IEEE Conference on Computer Vision and Pattern Recognition, Nashville, Tennessee, USA, May, 2025
DOI: 10.48550/arXiv.2505.12745
[ESWA] HaluCheck: Explainable and verifiable automation for detecting hallucinations in LLM responses
Expert Systems with Applications, Vol. 272, 126712, May, 2025
DOI: 10.1016/j.eswa.2025.126712
[JSID] Investigating the Effects of Degradation and Restoration on Face Recognition in Under-Display Cameras
Journal of the Society for Information Display, May, 2025
DOI: 10.1002/jsid.2090
[ICLR] ADAM Optimization with Adaptive Batch Selection
Proceedings of the 13th International Conference on Learning Representations, Singapore, April, 2025
Link
[ICLR] Adaptive Camera Sensor for Vision Models
Proceedings of the 13th International Conference on Learning Representations, Singapore, April, 2025
DOI: 10.48550/arXiv.2503.02170
[ICLR] Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
Proceedings of the 13th International Conference on Learning Representations, Singapore, April, 2025
DOI: 10.48550/arXiv.2503.05306
[ICLR] CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution
Proceedings of the 13th International Conference on Learning Representations, Singapore, April, 2025
Link
[ICLR] Dynamic Assortment Selection and Pricing with Censored Preference Feedback
Proceedings of the 13th International Conference on Learning Representations, Singapore, April, 2025
DOI: 10.48550/arXiv.2504.02324
[ICLR] Lasso Bandit with Compatibility Condition on Optimal Arm
Proceedings of the 13th International Conference on Learning Representations, Singapore, April, 2025
DOI: 10.48550/arXiv.2406.00823
[ICLR] Minimax Optimal Reinforcement Learning with Quasi-Optimism
Proceedings of the 13th International Conference on Learning Representations, Singapore, April, 2025
DOI: 10.48550/arXiv.2503.00810
[ASPLOS] ZRAID: Leveraging Zone Random Write Area (ZRWA) for Alleviating Partial Parity Tax in ZNS RAID
Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Vol. 1, pp. 1151-1165, Rotterdam, Netherlands, March, 2025
DOI: 10.1145/3669940.3707248
[BMC] De-identifcation of clinical notes with pseudo-labeling using regular expression rules and pre-trained BERT
BMC Medical Informatics and Decision Making, February, 2025
DOI: 10.1186/s12911-025-02913-z
[WACV] Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling
Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision, pages 5550-5559, Tucson, Arizona, USA, February, 2025
DOI: 10.1109/WACV61041.2025.00542
[arXiv] ANPMI: Assessing the True Comprehension Capabilities of LLMs for Multiple Choice Questions
February, 2025
arXiv: 2502.18798
[arXiv] GraphCheck: Multi-Path Fact-Checking with Entity-Relationship Graphs
February, 2025
arXiv: 2502.20785
[arXiv] Mind the Gap: Aligning the Brain with Language Models Requires a Nonlinear and Multimodal Approach
February, 2025
arXiv: 2502.12771
[COLING] Improving NMT models by REtrofitting Quality Estimators into Trainable Energy Loss
Proceedings of the 31st International Conference on Computational Linguistics, pages 8184–8196, Abu Dhabi, UAE, January, 2025
Link
[arXiv] FED: Fast and Efficient Dataset Deduplication Framework with GPU Acceleration
January, 2025
arXiv: 2501.01046
[arXiv] Integrating Spatial and Frequency Information for Under-Display Camera Image Restoration
January, 2025
arXiv: 2501.18517
[npj Digit. Med.] Explainable vision transformer for automatic visual sleep staging on multimodal PSG signals
npj Digital Medicine, Vol. 8, 55, January, 2025
DOI: 10.1038/s41746-024-01378-0
2024
[ECCV] Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation
Proceedings of the 18th European Conference on Computer Vision, pp. 121–137, Malmö, Sweden, December, 2024
DOI: 10.1007/978-3-031-72890-7_8
[JOK] LLMEE: 시각적 Token Attribution을 통한 대규모 언어 모델의 설명 가능성 및 평가 강화
Journal of KIISE, Vol.51, no.12, pp. 1104-1114, December, 2024
Link
[NeurIPS] Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference
Proceedings of the 38th Conference on Neural Information Processing Systems, pages 19813-19838, Vancouver, BC, Canada, December, 2024
Link
[NeurIPS] Improved Regret of Linear Ensemble Sampling
Proceedings of the 38th Conference on Neural Information Processing Systems, pages 92803-92831, Vancouver, BC, Canada, December, 2024
DOI: 10.48550/arXiv.2411.03932
[NeurIPS] Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
Proceedings of the 38th Conference on Neural Information Processing Systems, pages 77525-77592, Vancouver, BC, Canada, December, 2024
DOI: 10.48550/arXiv.2411.12878
[NeurIPS] Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
Proceedings of the 38th Conference on Neural Information Processing Systems, Vancouver, BC, Canada, December, 2024
DOI: 10.48550/arXiv.2405.09831
[NeurIPS] Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
Proceedings of the 38th Conference on Neural Information Processing Systems, pages 76643-76720, Vancouver, BC, Canada, December, 2024
DOI: 10.48550/arXiv.2405.20165
[NeurIPS] Self-Guided Masked Autoencoder
Proceedings of the 38th Conference on Neural Information Processing Systems, pages 58929-58954, Vancouver, BC, Canada, December, 2024
Link
[SIGIR-AP] AU-RAG: Agent-based Universal Retrieval Augmented Generation
Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, pages 2-11, Tokyo, Japan, December, 2024
DOI: 10.1145/3673791.3698416
[TACL] Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models
Transactions of the Association for Computational Linguistics, Vol. 12, pages 1686–1702, December, 2024
DOI: 10.1162/tacl_a_00724
[한국정보과학회] Analysis of Large Language Model Performance According to Korean-English Training Data Ratio in Continual Learning
한국정보과학회 2024년 한국소프트웨어종합학술대회 논문집, December, 2024
[BMVC] A Revisit to the Decoder for Camouflaged Object Detection
Proceedings of the 35th British Machine Vision Conference, Glasgow, UK, November, 2024
DOI: 10.48550/arXiv.2503.14035
[BMVC] Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space
Proceedings of the 35th British Machine Vision Conference, Glasgow, UK, November, 2024
DOI: 10.48550/arXiv.2409.05260
[EMNLP] Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22255–22269, Miami, Florida, USA, November, 2024
DOI: 10.18653/v1/2024.emnlp-main.1242
[EMNLP] Generalizing Clinical De-identification Models by Privacy-safe Data Augmentation using GPT-4
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21204–21218, Miami, Florida, USA, November, 2024
[EMNLP] Model-based Preference Optimization in Abstractive Summarization without Human Feedback
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18837-18851, Miami, Florida, USA, November, 2024
DOI: 10.18653/v1/2024.emnlp-main.1048
[EMNLP] RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22149–22161, Miami, Florida, USA, November, 2024
DOI: 10.18653/v1/2024.emnlp-main.1236
[IEEE Access] Toward Generalized Visualization System for Various CNN Models: Module and Layer View
IEEE Access, Vol. 12, pages 158311-158321, October, 2024
DOI: 10.1109/ACCESS.2024.3480791
[Sci Rep] Piano performance evaluation dataset with multilevel perceptual features
Scientific Reports, Vol. 14, 23002, October, 2024
DOI: 10.1038/s41598-024-73810-0
[UbiComp] MIRROR: Towards Generalizable On-Device Video Virtual Try-On for Mobile Shopping
Proceedings of the 2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Vol. 7, pp 1-27, Melbourne, Australia, October, 2024
DOI: 10.1145/3631420
[한국인공지능학회] A Unified Formulation and Analysis of Learning Algorithms with Output Constraints
2024 한국인공지능학회 하계학술대회, August, 2024
[한국인공지능학회] Case-Based Reasoning Approach for Solving Financial Question Answering
2024 한국인공지능학회 하계학술대회, August, 2024
[한국인공지능학회] Generalizing Table Reasoning Capability Under Domain Shift
2024 한국인공지능학회 하계학술대회, August, 2024
[한국인공지능학회] Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models
2024 한국인공지능학회 하계학술대회, August, 2024
[ICML] Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
Proceedings of the 41st International Conference on Machine Learning, pages 17224-17245, Vienna, Austria, July, 2024
DOI: 10.48550/arXiv.2407.11451
[ICML] On Positivity Condition for Causal Inference
Proceedings of the 41st International Conference on Machine Learning, pages 20818-20841, Vienna, Austria, July, 2024
Link
[SIGIR] Content-based Graph Reconstruction for Cold-start item recommendation
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1263-1273, Washington DC, USA, July, 2024
DOI: 10.1145/3626772.3657801
[UAI] Causal Discovery with Deductive Reasoning: One Less Problem
Proceedings of the 2024 Fortieth Conference on Uncertainty in Artificial Intelligence, pages 1999-2017, Barcelona, Spain, July, 2024
Link
[CVPR] Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains
Proceedings of the 40th IEEE Conference on Computer Vision and Pattern Recognition, pages 22294-22303, Seattle, Washington, USA, June, 2024
DOI: 10.1109/CVPR52733.2024.02104
[NAACL] Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
Findings of the Association for Computational Linguistics: NAACL 2024, pages 1809–1820, Mexico City, Mexico, June, 2024
DOI: 10.18653/v1/2024.findings-naacl.117
[arXiv] Locate&Edit: Energy-based Text Editing for Efficient, Flexible, and Faithful Controlled Text Generation
June, 2024
arXiv: 2407.00740
[한국정보과학회] Contrastive Learning Framework for Session-Based Recommendation
한국정보과학회 2024년 한국컴퓨터종합학술대회 논문집, June, 2024
[한국정보과학회] QAT-Clip: Transformer 기반 언어 모델 양자화를 위한 Fine-tuning 중 이상치 제거
한국정보과학회 2024년 한국컴퓨터종합학술대회 논문집, June, 2024
[한국정보과학회] 사전 훈련 말뭉치에 따른 언어 모델의 성능 및 영향 분석
한국정보과학회 2024 한국컴퓨터종합학술대회 논문집, pages 996-998, June, 2024
Link
[AISTATS] Towards a Complete Benchmark on Video Moment Localization
Proceedings of the 27th International Conference on Artificial Intelligence and Statistics, pages 4168-4176, Valencia, Spain, May, 2024
Link
[ICLR] Demystifying Linear MDPs and Novel Dynamics Aggregation Framework
Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria, May, 2024
DOI: 10.48550/arXiv.2410.24089
[ICLR] Dictionary Contrastive Forward Learning via Adaptive Label Embeddings
Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria, May, 2024
Link
[ASPLOS] TCCL: Discovering Better Communication Paths for PCIe GPU Clusters.
ASPLOS 2024: Proceedings of the 29th International Conference on Architectural Support for Programming Languages and Operating Systems, Vol. 3, pp. 999-1015, San Diego, USA, April, 2024
DOI: 10.1145/3620666.3651362
[PAKDD] Human-driven Active Verification for Efficient and Trustworthy Graph Classification
Proceedings of the 28th Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 105-116, Taipei, Taiwan, April, 2024
DOI: 10.1007/978-981-97-2242-6_9
[AAAI] Learning Uncertainty-Aware Temporally-Extended Actions
Proceedings of the 38th AAAI Conference on Artificial Intelligence, pages 13391-13399, Vancouver, Canada, March, 2024
DOI: 10.1609/aaai.v38i12.29241
[AAAI] V2Meow: Meowing to the Visual Beat via Video-to-Music Generation
Proceedings of the 38th AAAI Conference on Artificial Intelligence, pages 4952-4960, Vancouver, Canada, March, 2024
DOI: 10.1609/aaai.v38i5.28299
[FAST] RFUSE: Modernizing Userspace Filesystem Framework through Scalable Kernel-Userspace Communication
Proceedings of the 22nd USENIX Conference on File and Storage Technologies, pages 141-157, Santa Clara, CA, USA, February, 2024
Link
[WACV] Modality-Aware Representation Learning for Zero-shot Sketch-based Image Retrieval
Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision, pages 5634-5643, Waikoloa, Hawaii, January, 2024
DOI: 10.1109/WACV57701.2024.00555
[WACV] PoseDiff: Pose-conditioned Diffusion for Sparse View Unbounded Scene Synthesis
Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision, pages 5005-5015, Waikoloa, Hawaii, January, 2024
DOI: 10.1109/WACV57701.2024.00494
2023
[ICDM] Toward Interpretable Graph Neural Networks via Concept Matching Model
2023 IEEE International Conference on Data Mining, pages 950-955, Gyeongju, Republic of Korea, December, 2023
DOI: 10.1109/ICDM58522.2023.00106
[NeurIPS] Cascading Contextual Assortment Bandits
Proceedings of the 37th Conference on Neural Information Processing Systems, pages 23441-23452, New Orleans, LA, USA, December, 2023
Link
[NeurIPS] Mr. HiSum: A Large-scale Dataset and Benchmark for Video Highlight Detection and Summarization
Proceedings of the 37th Conference on Neural Information Processing Systems, pages 40542-40555, New Orleans, LA, USA, December, 2023
Link
[NeurIPS] UDC-SIT: A Real-World Dataset for Under-Display Cameras
Proceedings of the 37th Conference on Neural Information Processing Systems, pages 67721-67740, New Orleans, LA, USA, December, 2023
[ICCV] A Unified Framework for Robustness on Diverse Sampling Errors
Proceedings of the 19th IEEE/CVF International Conference on Computer Vision, pages 1464-1472, Paris, France, October, 2023
DOI: 10.1109/ICCV51070.2023.00141
[ICCV] Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild
Proceedings of the 19th IEEE/CVF International Conference on Computer Vision, pages 14726-14736, Paris, France, October, 2023
DOI: 10.1109/ICCV51070.2023.01357