Publications_1 - National AI Research Lab

#Breakthrough in Neural Scaling Law

WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image

연도: 2025 / 저자: 박지우, 최태은, 전영준, 황성재 / 학술대회명: International Conference on Computer Vision (ICCV)

#Breakthrough in Neural Scaling Law

Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis

연도: 2025 / 저자: 한우정, 이연경, 김찬영, 박광현, 황성재 / 학술대회명: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

#Breakthrough in Neural Scaling Law

Your Large Vision-Language Model Only Needs A Few Attention Heads for Visual Grounding

연도: 2025 / 저자: 강세일, 김진영, 김준혁, 황성재 / 학술대회명: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

#Breakthrough in Neural Scaling Law

Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation

연도: 2025 / 저자: 김찬영, 주다윤, 한우정, Ming-Hsuan Yang, 황성재 / 학술대회명: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

#Breakthrough in Neural Scaling Law

Interpreting vision transformers via residual replacement model

연도: 2025 / 저자: 김진영, 김준혁, 심유민, 김주혁, 정선영, 황성재 / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

Rare Text Semantics Were Always There in Your Diffusion Transformer

연도: 2025 / 저자: 강세일, 한우정, 주다윤, 황성재 / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

Information-Theoretic Discrete Diffusion

연도: 2025 / 저자: 전문규, 신상우, 전동재, Albert No / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment

연도: 2025 / 저자: 정원제, 윤상연, 강민석, Albert No / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition

연도: 2025 / 저자: 조윤준, 김소은, 전동재, 이계림, 이범수, Albert No / 학술대회명: Annual Meeting of the Association for Computational Linguistics (ACL)

#Breakthrough in Neural Scaling Law

R-TOFU: Unlearning in Large Reasoning Models

연도: 2025 / 저자: 윤상연, Wonje Jeung, Albert No / 학술대회명: Conference on Empirical Methods in Natural Language Processing (EMNLP)

#Breakthrough in Neural Scaling Law

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes

연도: 2025 / 저자: 전동재, 김두은, Albert No / 학술대회명: International Conference on Machine Learning (ICML)

#Breakthrough in Neural Scaling Law

MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables

연도: 2025 / 저자: 서광욱, 권동욱, 이동하 / 학술대회명: Annual Meeting of the Association for Computational Linguistics (ACL)

#Breakthrough in Neural Scaling Law

Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts

연도: 2025 / 저자: 윤수진, 고성호, 김통영, 강성구, 여진영, 이동하 / 학술대회명: ACM International Conference on Web Search and Data Mining (WSDM)

#Breakthrough in Neural Scaling Law

Stop Playing the Guessing Game! Target-Free User Simulation for Evaluating Conversational Recommender Systems

연도: 2025 / 저자: 김성환, 서광욱, 김통영, 여진영, 이동하 / 학술대회명: Conference on Empirical Methods in Natural Language Processing (EMNLP)

#Breakthrough in Neural Scaling Law

Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action

연도: 2025 / 저자: 김통영, 이정은, 윤수진, 김성환, 이동하 / 학술대회명: Conference on Empirical Methods in Natural Language Processing (EMNLP)

#Breakthrough in Neural Scaling Law

Can Large Language Models be Effective Online Opinion Miners?

연도: 2025 / 저자: 허량, 서용식, 이준성, 이동하 / 학술대회명: Conference on Empirical Methods in Natural Language Processing (EMNLP)

#Breakthrough in Neural Scaling Law

Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models

연도: 2025 / 저자: 조인, 유영범, 전수빈, 김선주 / 학술대회명: International Conference on Computer Vision (ICCV)

#Breakthrough in Neural Scaling Law

Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation

연도: 2025 / 저자: 허미란, 오성욱, 김선주, 이준영 / 학술대회명: The Association for the Advancement of Artificial Intelligence (AAAI)

#Breakthrough in Neural Scaling Law

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

연도: 2025 / 저자: 소준혁, 이치웅, 이신영, 옥정슬, 박은혁 / 학술대회명: Conference on Neural Information Processing Systems (NeurIPS)

#Breakthrough in Neural Scaling Law

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks

연도: 2025 / 저자: 이동우, 이동복, Steven Adriaensen, 이주호, 황성주, Frank Hutter, 김선주, 이해범 / 학술대회명: International Conference on Machine Learning (ICML)

연구논문