선도 연구 주제

전체 논문

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

← 연구 아카이브로 돌아가기

All 317 Beyond Scaling Laws 155 Physical AI & Robotics 104 High-dimensional Generative Models 58

Beyond Scaling Laws

논문 155개

# Breakthrough in Neural Scaling Law

Position: The Term “Machine Unlearning” Is Overused in LLMs

Sangyeon Yoon, Yeachan Jun, Albert No · ICML · 2026

# Breakthrough in Neural Scaling Law

Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation?

Hyowon Wi, Noseong Park · ACL · 2026

# Breakthrough in Neural Scaling Law

Incomplete Prompt Jailbreaks in Large Language Models

Yeonjea Kim, Bumjin Park, Jaesik Choi · ACL Findings · 2026

# Breakthrough in Neural Scaling Law

Bringing Real-World Relations into Video Generation with Graph-Structured Knowledge

Joonhyung Park, Jaeyun Song, Sihwan Park, Eunho Yang · ACL · 2026

# Breakthrough in Neural Scaling Law

Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes

Yehna Kim, Young-Eun Kim, Seong-Whan Lee · Pattern Recognition · 2026

# Breakthrough in Neural Scaling Law

Anchoring and Rescaling Attention for Semantically Coherent Inbetweening

TaeEun Choi, Sumin Shim, Junhyeok Kim, Seong Jae Hwang · CVPR · 2026

# Breakthrough in Neural Scaling Law

Interpretable Motion Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers

Youngjun Jun, Seil Kang, Woojung Han, Seong Jae Hwang · CVPR · 2026

# Breakthrough in Neural Scaling Law

ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting

Yeonkyung Lee, Dayun Ju, Youngmin Kim, Seil Kang, Seong Jae Hwang · CVPR · 2026

# Breakthrough in Neural Scaling Law

FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics

Taejin Jeong, Joohyeok Kim, Jinyeong Kim, Chanyoung Kim, Seong Jae Hwang · CVPR · 2026

# Breakthrough in Neural Scaling Law

Rethinking Glaucoma Calibration: Voting-Based Binocular and Metadata Integration

Taejin Jeong, Joohyeok Kim, Jaehoon Joo, Seong Jae Hwang · ISBI · 2026