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

Liang Shi

ICLR 2026SIGIR 2026推理智能体与工具对齐与偏好
新星分新星
82
一作贡献80
核心/参与0
方向广度9
合作网络6
2 一作 · 2 篇 · ICLR 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
一作SIGIR 2026Oral· Information Retrieval (Full)

TAR: Generative Auto-Bidding and Budget Pacing via Multi-Scale Trajectory Modeling

Liang Shi · Longxiang Xu (Taobao &amp · Tmall Group of Alibaba) · Tmall Group of Alibaba) · Yundu Huang (Taobao &amp · Tmall Group of Alibaba) · Yundu Huang (Taobao &amp · Shengjie Sun (Taobao &amp · Tmall Group of Alibaba)

摘要

Auto-bidding and budget pacing are formulated as sequential decision-making tasks. While flexible, such a framework faces a fundamental granularity mismatch: decisions are made at a fine temporal scale, while their performance feedback is fully and reliably observable at a much coarser resolution...

推理智能体与工具对齐与偏好OpenReview

常见合作者