Scientific Frontiers

Publications

The complete index of NAIRL’s published research across its three scientific frontiers.

← Back to Research Archive

All Publications

442 publications
# 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
# Breakthrough in Neural Scaling Law

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

Thanh-Long V. Le, Myeongho Jeon, Kim Vu, Viet Lai, Eunho Yang · ICLR · 2026
# Breakthrough in Neural Scaling Law

Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding

Seongwoong Shim, Myunsoo Kim, Jae Hyeon Cho, Byung-Jun Lee · ICLR · 2026
# Breakthrough in Neural Scaling Law

SCAD: Super-Class-Aware Debiasing for Long-Tailed Semi-Supervised Learning

Sunguk Jang, Jinwoo Jeon, Byung-Jun Lee · ICLR · 2026
# Breakthrough in Neural Scaling Law

FALCON: False-Negative Aware Learning of Contrastive Negatives in Vision-Language Alignment

Myunsoo Kim, Seongwoong Shim, Byung-Jun Lee · CVPR · 2026
# Breakthrough in Neural Scaling Law

An Information Theoretic Evaluation Metric for Strong Unlearning

Dongjae Jeon, Wonje Jeung, Taeheon Kim, Albert No, Jonghyun Choi · AAAI · 2026
# Breakthrough in Neural Scaling Law

A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models

Wonje Jeung, Sangyeon Yoon, Yoonjun Cho, Dongjae Jeon, Sangwoo Shin, Hyesoo Hong, Albert No · ICLR · 2026
# Breakthrough in Neural Scaling Law

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures

Sangyeon Yoon, Hyesoo Hong, Wonje Jeung, Albert No · ICLR · 2026
# Breakthrough in Neural Scaling Law

Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings

Bumjun Kim, Albert No · CVPR Findings · 2026