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

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

Su Ho Han, Jeongseok Hyun, Pilhyeon Lee, Minho Shim, Dongyoon Wee, Seon Joo Kim · ICLR · 2026

# Breakthrough in Neural Scaling Law

Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors

Subin Jeon, In Cho, Junyoung Hong, Woong Oh Cho, Seon Joo Kim · CVPR · 2026

# Breakthrough in Neural Scaling Law

Effective Dataset Distillation for Spatio-Temporal Forecasting with Bi-dimensional Compression

Yeonje Choi, Taehyung Kwon, Yeongho Kim, Kijung Shin · ICDE · 2026

# Breakthrough in Neural Scaling Law

Personalized Parameter-Efficient Fine-Tuning of Foundation Models for Multimodal Recommendation

Sunwoo Kim, Hyunjin Hwang, Kijung Shin · WWW · 2026

# Breakthrough in Neural Scaling Law

Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs

Jeongwhan Choi, Seungjun Park, Sumin Park, Sung-Bae Cho, Noseong Park · AAAI · 2026

# Breakthrough in Neural Scaling Law

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

Jeongwhan Choi, Jongwoo Kim, Woosung Kang, Noseong Park · ICLR · 2026

# Breakthrough in Neural Scaling Law

Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation

Yehjin Shin, Seojin Kim, Noseong Park · ICLR · 2026

# Breakthrough in Neural Scaling Law

TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection

Yearang Lee, Ho-Joong Kim, Seong-Whan Lee · CVPR · 2026

# Breakthrough in Neural Scaling Law

PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models

Eunyeong Cho, Jehyeon Bang, Ranggi Hwang, Minsoo Rhu · HPCA · 2026

# Breakthrough in Neural Scaling Law

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Heecheol Yun, Kwangmin Ki, Junghyun Lee, Eunho Yang · ICLR · 2026