paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
NL

Nakyung Lee

NeurIPS 2026×2ACL 2026可解释性社会与人本长上下文与架构推理评测与基准
新星分新星
82
一作贡献70
核心/参与5
方向广度13
合作网络6
2 一作 · 3 篇 · NeurIPS 2026 / ACL 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

3
一作NeurIPS 2026Poster· Social Aspects / Accountability, Transparency and Interpretability

Mechanistic Circuit Identification for Controllable Data Generation

Nakyung Lee · Sangwoo Hong · Jungwoo Lee

可解释性社会与人本OpenReview
一作ACL 2026Poster· Natural Language Processing

Efficient Process Reward Modeling via Contrastive Mutual Information

Nakyung Lee · Sangwoo Hong · Jungwoo Lee

摘要

Recent research has devoted considerable effort to verifying the intermediate reasoning steps of chain-of-thought (CoT) trajectories using process reward models (PRMs) and other verifier models. However, training a PRM typically requires human annotators to assign reward scores to each reasoning...

推理评测与基准对齐与偏好OpenReview 项目页

常见合作者