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

Ziheng Ni

SIGIR 2026×2ICLR 2026对齐与偏好可解释性强化学习与后训练
新星分新星
63
一作贡献30
核心/参与10
方向广度9
合作网络6
1 一作 · 3 篇 · SIGIR 2026 / ICLR 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
作者位次 #3/6SIGIR 2026Poster· Information Retrieval (Industry)

DPEO: Dynamic Preference Evolution Optimization for Self-Evolving CTR Prediction

Kun Yao · Congcong Liu · Ziheng Ni · Wenlong Chen · Changping Peng · Ching Law

摘要

Click-through rate (CTR) prediction is a pivotal component in large-scale industrial systems. Historically, CTR prediction paradigms have been confined to monolithic architectures governed by a single-policy optimization process. However, such isolated learning paths lack the intrinsic evolutiona...

对齐与偏好可解释性强化学习与后训练OpenReview
作者位次 #3/7SIGIR 2026Poster· Information Retrieval (Industry)

AIPO: Adaptive Anchored Intent-aware Policy Optimization for Generative Recommendation

Kun Yao · Congcong Liu · Ziheng Ni · Cai Shang · Wenlong Chen · Changping Peng · Ching Law

摘要

Generative Recommendation (GenRec) has emerged as a significant evolutionary direction in the field of recommendation systems in recent years. However, during the reinforcement learning (RL) alignment stage of end-to-end GenRec, a core challenge is that the low signal-to-noise ratio (SNR) of feed...

强化学习与后训练对齐与偏好可解释性OpenReview

常见合作者