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

전체 논문

논문 317개

# Foundation Model for Robotics

DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning

Junha Lee, Eunha Park, Minsu Cho · CVPR · 2026

# Foundation Model for Robotics

Affostruction: 3D Affordance Grounding with Generative Reconstruction

Chunghyun Park, Seunghyeon Lee, Minsu Cho · CVPR · 2026

# Foundation Model for Robotics

Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization

Taeyoon Kwon*, Dongwook Choi*, Hyojun Kim, Sunghwan Kim, Seungjun Moon, Beong-woo Kwak, Kuan-Hao Huang, Jinyoung Yeo · ICLR · 2026

# Breakthrough in Neural Scaling Law

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization

Taehyeok Ha, Jaeho Lee · ICML · 2026

# Breakthrough in Neural Scaling Law

Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models

Jaeho Lee · ACL · 2026

# Breakthrough in Neural Scaling Law

Speculative End-Turn Detector for Efficient Speech Chatbot Assistant

Suho Yoo, Jaeho Lee · ACL · 2026

# Breakthrough in Neural Scaling Law

TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning

Hayeong Lee, JunHyeok Oh, Byung-Jun Lee · ICML · 2026

# Breakthrough in Neural Scaling Law

Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset

Geon Choi, Hangyul Yoon, Hyunju Shin, Hyunki Park, Sang Hoon Seo, Eunho Yang, Edward Choi · CVPR · 2026

# Foundation Model for Robotics

Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers

Lee Hyoseok, Sohwi Lim, Eunju Cha, Tae-Hyun Oh · ICML · 2026

# Foundation Model for Robotics

A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search

Baek Seong-Eun, Lee Jung-Mok, Kim Sung-Bin, Tae-Hyun Oh · ICML · 2026