paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

YW

Yong Wang

ICML 2026×4AAAI 2026×2KDD 2026强化学习与后训练可解释性多模态效率与系统推理

新星分贡献者

70

一作贡献0

核心/参与39

方向广度16

合作网络12

0 一作 · 7 篇 · ICML 2026 / AAAI 2026 / KDD 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

7

作者位次 #6/7ICML 2026Poster· Deep Learning / Large Language Models

D²Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning

Ru Zhang · Renda Li · Ziyu Ma · Weijie Qiu · Chongyang Tao · Yong Wang · Xiangxiang Chu

强化学习与后训练效率与系统OpenReview

作者位次 #6/8ICML 2026Poster· Deep Learning / Large Language Models

Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification

Tianyi Wang · Long Li · Hongcan Guo · Yibiao Chen · Yixia Li · Yong Wang · Yun Chen · Guanhua CHEN

强化学习与后训练OpenReview

作者位次 #5/7ICML 2026Poster· Deep Learning / Large Language Models

AIR: Post-training Data Selection for Reasoning via Attention Head Influence

Jinrui Liu · Kai Hua · Xuanguang Pan · Ge Zhang · Yong Wang · Shuai Ma · Chongyang Tao

推理可解释性强化学习与后训练OpenReview

作者位次 #4/7ICML 2026Poster· Deep Learning / Large Language Models

Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation

Zihan Su · Hongyang Wei · Kangrui Cen · Yong Wang · Guanhua CHEN · Chun Yuan · Xiangxiang Chu

可解释性多模态OpenReview

作者位次 #3/4KDD 2026Oral· Knowledge Discovery & Data Mining

Causal Estimation of Share-Induced Engagement with Flywheel Effects

Weitao Cheng · Yilin Li · Yong Wang · Nian Si

检索与知识OpenReview

作者位次 #4/6AAAI 2026Poster· Artificial Intelligence

Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning

Ziyu Ma · Chenhui Gou · Yiming Hu · Yong Wang · Bohan Zhuang · Jianfei Cai

多模态理论与学习动力学OpenReview

作者位次 #5/6AAAI 2026Poster· Artificial Intelligence

AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting

Renda Li · Hailang Huang · Fei Wei · Feng Xiong · Yong Wang · Xiangxiang Chu

强化学习与后训练OpenReview

常见合作者

RLRenda Li×2 CTChongyang Tao×2 XCXiangxiang Chu×2 GCGuanhua CHEN×2 RZRu Zhang ZMZiyu Ma WQWeijie Qiu TWTianyi Wang LLLong Li HGHongcan Guo YCYibiao Chen YLYixia Li