paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

AZ

Amy Zhang

ICLR 2026×6强化学习与后训练检索与知识评测与基准推理多模态

新星分资深

32

一作贡献0

核心/参与20

方向广度10

合作网络12

0 一作 · 6 篇 · 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

6

作者位次 #4/6ICLR 2026Poster· Reinforcement Learning / Deep RL

Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion

Dan Haramati · Carl Qi · Tal Daniel · Amy Zhang · Aviv Tamar · George D Konidaris

强化学习与后训练检索与知识OpenReview

作者位次 #6/9ICLR 2026Poster· Reinforcement Learning / Deep RL

Reevaluating Policy Gradient Methods for Imperfect-Information Games

Max Rudolph · Nathan Lichtlé · Sobhan Mohammadpour · Alexandre M Bayen · Zico Kolter · Amy Zhang · Gabriele Farina · Eugene Vinitsky · Samuel Sokota

强化学习与后训练评测与基准OpenReview

作者位次 #4/6ICLR 2026Poster· Reinforcement Learning / Deep RL

Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models

Pranaya Jajoo · Harshit Sikchi · Siddhant Agarwal · Amy Zhang · Scott Niekum · Martha White

强化学习与后训练OpenReview

作者位次 #8/9ICLR 2026Poster· Computer Vision / Classification and Understanding

Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning

Carl Qi · Xiaojie Wang · Silong Yong · Stephen Sheng · Huitan Mao · sriram srinivasan · Manikantan Nambi · Amy Zhang · Yeshwant Dattatreya

推理多模态OpenReview

作者位次 #4/4ICLR 2026Poster· Reinforcement Learning / Deep RL

Reinforcement Learning via Value Gradient Flow

Haoran Xu · Kaiwen Hu · Somayeh Sojoudi · Amy Zhang

强化学习与后训练OpenReview

作者位次 #3/3ICLR 2026Poster

Multi-agent Coordination via Flow Matching

Dongsu Lee · Daehee Lee · Amy Zhang

智能体与工具OpenReview

常见合作者

CQCarl Qi×2 DHDan Haramati TDTal Daniel ATAviv Tamar GKGeorge D Konidaris MRMax Rudolph NLNathan Lichtlé SMSobhan Mohammadpour ABAlexandre M Bayen ZKZico Kolter GFGabriele Farina EVEugene Vinitsky