선도 연구 주제

전체 논문

NAIRL이 세 가지 선도 연구 주제에 걸쳐 발표한 연구의 전체 색인입니다.

연구 아카이브로 돌아가기

Beyond Scaling Laws

논문 87개
# Breakthrough in Neural Scaling Law

See What You Are Told: Visual Attention Sink in Large Multimodal Models

Seil Kang, Jinyeong Kim, Junhyeok Kim, Seong Jae Hwang · ICLR · 2025
# Breakthrough in Neural Scaling Law

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

Jiwoo Park, Tae Eun Choi, Youngjun Jun, Seong Jae Hwang · ICCV · 2025
# Breakthrough in Neural Scaling Law

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

Woojung Han, Yeonkyung Lee, Chanyoung Kim, Kwanghyun Park, Seong Jae Hwang · CVPR · 2025
# Breakthrough in Neural Scaling Law

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

Seil Kang, Jinyeong Kim, Junhyeok Kim, Seong Jae Hwang · CVPR · 2025
# Breakthrough in Neural Scaling Law

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

Chanyoung Kim, Dayun Ju, Woojung Han, Ming-Hsuan Yang, Seong Jae Hwang · CVPR · 2025
# Breakthrough in Neural Scaling Law

Interpreting vision transformers via residual replacement model

Jinyeong Kim, Junhyeok Kim, Yumin Shim, Joohyeok Kim, Sunyoung Jung, Seong Jae Hwang · NeurIPS · 2025
# Breakthrough in Neural Scaling Law

Rare Text Semantics Were Always There in Your Diffusion Transformer

Seil Kang, Woojung Han, Dayun Ju, Seong Jae Hwang · NeurIPS · 2025
# Breakthrough in Neural Scaling Law

Information-Theoretic Discrete Diffusion

Moongyu Jeon, Sangwoo Shin, Dongjae Jeon, Albert No · NeurIPS · 2025
# Breakthrough in Neural Scaling Law

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

Wonje Jeung, Sangyeon Yoon, Minsuk Kahng, Albert No · NeurIPS · 2025
# Breakthrough in Neural Scaling Law

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

Yoonjun Cho, Soeun Kim, Dongjae Jeon, Kyelim Lee, Beomsoo Lee, Albert No · ACL · 2025