Publications_1 - National AI Research Lab

#Breakthrough in Neural Scaling Law

Enhancing Creative Generation on Stable Diffusion-based Models

연도: 2025 / 저자: 한지연 , 권다희 , 이가영 , 김준호 , 최재식 / 학술대회명: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

#Breakthrough in Neural Scaling Law

Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning

연도: 2025 / 저자: 이교운, 최재식 / 학술대회명: International Conference on Machine Learning (ICML)

#Breakthrough in Neural Scaling Law

State-Covering Trajectory Stitching for Diffusion Planners

연도: 2025 / 저자: 이교운, 최재식 / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain

연도: 2025 / 저자: 위효원, 최정환, 박노성 / 학술대회명: International Joint Conference on Artificial Intelligence (IJCAI)

#Breakthrough in Neural Scaling Law

Neural Functions for Learning Periodic Signal

연도: 2025 / 저자: 조우진, 조민주, 이국진, 박노성 / 학술대회명: International Conference on Learning Representations (ICLR)

#Breakthrough in Neural Scaling Law

SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation

연도: 2025 / 저자: 이채정, 최정환, 위효원, 조성배, 박노성 / 학술대회명: ACM International Conference on Web Search and Data Mining (WSDM)

#Breakthrough in Neural Scaling Law

Debunking the CUDA Myth Towards GPU-based AI Systems: Evaluation of the Performance and Programmability of Intel’s Gaudi NPU for AI Model Serving

연도: 2025 / 저자: 이윤재, 임준택, 방재현, 조은영, 정휘종, 김태수, 김형준, 이준형, 임진섭, 황랑기, 권세정, 이동수, 류민수 / 학술대회명: International Symposium on Computer Architecture (ISCA)

#Breakthrough in Neural Scaling Law

Mamba-X: An End-to-End Vision Mamba Accelerator for Edge Computing Devices

연도: 2025 / 저자: 윤동호, 이궁규, 장재원, 이윤재, 이동재, 류민수 / 학술대회명: International Conference on Computer-Aided Design (ICCAD)

#Breakthrough in Neural Scaling Law

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets

연도: 2025 / 저자: 김유준, 문채원, 윤철희 / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty

연도: 2025 / 저자: 조예슬, 신백록, 강창민, 윤철희 / 학술대회명: International Conference on Machine Learning (ICML)

#Breakthrough in Neural Scaling Law

Self-Training Elicits Concise Reasoning in Large Language Models

연도: 2025 / 저자: Tergel Munkhbat , 호남규 , 김서현 , 양용진 , 김유진 , 윤세영 / 학술대회 논문: Annual Meeting of the Association for Computational Linguistics (ACL)

#Breakthrough in Neural Scaling Law

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

연도: 2025 / 저자: 배상민, 김유진, Reza Bayat, 김성륜, 하지윤, Tal Schuster, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Aaron Courville, 윤세영 / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

연도: 2025 / 저자: 고종우, Tianyi Chen, 김성년, Tianyu Ding, Luming Liang, Ilya Zharkov, 윤세영 / 학술대회 논문: International Conference on Machine Learning (ICML)

#Breakthrough in Neural Scaling Law

Beyond Neighbors: Distance-Generalized Graphlets for Enhanced Graph Characterization

연도: 2025 / 저자: 김영호, 김유영, 이건, 신기정 / 학술대회명: The ACM Web Conference (WWW)

#Breakthrough in Neural Scaling Law

Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding

연도: 2025 / 저자: 김선우, 황현진, 신기정 / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

‘Hello, World!’: Making GNNs Talk with LLMs

연도: 2025 / 저자: 김선우, 이수용, 유재민, 신기정 / 학술대회명: Conference on Empirical Methods in Natural Language Processing (EMNLP)

#Breakthrough in Neural Scaling Law

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

연도: 2025 / 저자: 장두혁, 박시환, 양준용, 정연성, 윤지훈, Souvik Kundu, 김성엽, 양은호 / 학술대회명: International Conference on Learning Representations (ICLR)

#Breakthrough in Neural Scaling Law

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning

연도: 2025 / 저자: 류현, 김경만, 이혜민, 양은호 / 학술대회명: International Conference on Learning Representations (ICLR)

#Breakthrough in Neural Scaling Law

Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing

연도: 2025 / 저자: 김주원, 이지석, 조동현, 조상현, 정연성, 김경수, 양은호 / 학술대회명: IEEE/CVF International Conference on Computer Vision (ICCV)

#Breakthrough in Neural Scaling Law

Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens

연도: 2025 / 저자: 김소희, 류수현, 박준형, 양은호 / 학술대회 논문: Conference on Empirical Methods in Natural Language Processing (EMNLP)

연구논문