paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

JW

Jie Wang

ICLR 2026×8推理可解释性强化学习与后训练数据与预训练代码

新星分贡献者

83

一作贡献0

核心/参与75

方向广度10

合作网络12

0 一作 · 8 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

8

作者位次 #2/9ICLR 2026Poster· Deep Learning / Attention Mechanisms

Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis

Qingyue Yang · Jie Wang · Xing Li · Yinqi Bai · Tong Xialiang · Huiling Zhen · Jianye Hao · Mingxuan Yuan · Bin Li

可解释性OpenReview

作者位次 #2/7ICLR 2026Poster· Applications / Physics

Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter

Hong Wang · Jie Wang · Jian Luo · huanshuo dong · Yeqiu Chen · Runmin Jiang · Zhen Huang

数据与预训练OpenReview

作者位次 #2/7ICLR 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning

Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance

Xiaoqi Ni · Jie Wang · Lin Yang · Yiyang Lu · Hanzhu Chen · Rui Liu · Jianye Hao

推理OpenReview

作者位次 #3/9ICLR 2026Poster· Deep Learning / Everything Else

Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization

Xize Liang · Lin Yang · Jie Wang · Rui Liu · Yang Lu · Jinliang Zeng · Hanzhu Chen · Dong Li · Jianye Hao

推理强化学习与后训练OpenReview

作者位次 #2/9ICLR 2026Poster· Applications / Everything Else

Evolving Graph Structured Programs for Circuit Generation with Large Language Models

Yinqi Bai · Jie Wang · Lei Chen · Zhihai Wang · Yumeng Li · Mingxuan Yuan · Jianye Hao · Defu Lian · Enhong Chen

可解释性代码OpenReview

作者位次 #2/7ICLR 2026Poster· Applications / Neuroscience, Cognitive Science

A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic Optimization

Yinqi Bai · Jie Wang · Tong Xialiang · Longdi Pan · Jilai Pan · Mingxuan Yuan · Jianye Hao

推理可解释性效率与系统OpenReview

作者位次 #3/7ICLR 2026Poster· Deep Learning / Everything Else

Latent-Guided Reasoning: Empowering Small LLMs with Large-Model Thinking

Hanzhu Chen · Lin Yang · Jie Wang · Junhao Yan · Zhe Wang · Xize Liang · Jianye Hao

推理OpenReview

作者位次 #6/7ICLR 2026Poster· Theory / Reinforcement Learning and Planning

Tackling Heavy-Tailed Q-Value Bias in Offline-to-Online Reinforcement Learning with Laplace-Robust Modeling

Ruibo Guo · Lei Liu · Rui Yang · Junjie Shen · Guoping Wu · Jie Wang · Bin Li

推理强化学习与后训练社会与人本OpenReview

常见合作者

JHJianye Hao×6 YBYinqi Bai×3 MYMingxuan Yuan×3 LYLin Yang×3 HCHanzhu Chen×3 TXTong Xialiang×2 BLBin Li×2 RLRui Liu×2 XLXize Liang×2 QYQingyue Yang XLXing Li HZHuiling Zhen