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

Yankun Le

ACL 2026SIGIR 2026可解释性对齐与偏好推理检索与知识
新星分新星
68
一作贡献40
核心/参与5
方向广度11
合作网络6
1 一作 · 2 篇 · ACL 2026 / SIGIR 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

2
作者位次 #6/8ACL 2026Poster· Natural Language Processing

Exploring Layer Activation Dynamic of C o T via Knowledge Probe

Chuanxin Zhang · Jiajun Liu · Yao He · Wenjun Ke · Peng Wang · Yankun Le · Sirui Liu · Zhaoyu Yang

摘要

Chain-of-thought (CoT) reasoning has emerged as a crucial paradigm for enhancing large language model (LLM) performance on multi-step reasoning tasks.However, the internal mechanisms by which LLMs invoke knowledge and propagate information across different steps of the CoT are poorly understood.T...

可解释性推理对齐与偏好OpenReview 项目页
一作SIGIR 2026Oral· Information Retrieval (Full)

Countering Interest Over-Smoothing: Distilling Latent Factors via Diffusion for Multi-Interest Retrieval

Yankun Le · Fu Zhang · Haoran Li · Baoyuan Ou · Yingjie Qin · Zhixuan Yang · Ruilong Su

摘要

Multi-interest recommendation is essential for the matching stage. By generating multiple user representations, it can better cover the diverse interests derived from user interaction history. Ideally, multi-interest models should effectively identify the underlying latent factors — the specific...

检索与知识对齐与偏好可解释性OpenReview

常见合作者