paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

YS

Ye Shi

ICML 2026×7AAAI 2026评测与基准强化学习与后训练效率与系统多模态

新星分资深

33

一作贡献0

核心/参与20

方向广度11

合作网络12

0 一作 · 8 篇 · ICML 2026 / AAAI 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 #3/5ICML 2026Poster

FedEBA+: Towards Fair and Effective Federated Learning via Entropy-Based Model

Zhichao Wang · Lin Wang · Ye Shi · Sai Praneeth Reddy Karimireddy · Xiaoying Tang

作者位次 #4/7ICML 2026Poster· General Machine Learning / Evaluation

Conformal Reliability: A New Evaluation Metric for Conditional Generation

Yachen Gao · Xinwei Sun · Yikai Wang · Ye Shi · Jingya Wang · Jianfeng Feng · Yanwei Fu

评测与基准OpenReview

作者位次 #8/8ICML 2026Poster· Applications / Robotics

Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation

Zhaoyang Liu · Mokai Pan · Zhongyi Wang · Kaizhen Zhu · Haotao Lu · Haipeng Zhang · Jingya Wang · Ye Shi

作者位次 #6/6ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis

Kaizhen Zhu · Mokai Pan · Zhechuan Yu · Jingya Wang · Jingyi Yu · Ye Shi

作者位次 #7/7ICML 2026Poster· Optimization / Non-Convex

Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement

Shutong Ding · Yimiao Zhou · Ke Hu · Xi Yao · Junchi Yan · Xiaoying Tang · Ye Shi

作者位次 #7/7ICML 2026Poster· Reinforcement Learning / Online

Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance

Shutong Ding · Zejia Zhong · Zhongyi Wang · Ke Hu · Bikang Pan · Jingya Wang · Ye Shi

强化学习与后训练效率与系统OpenReview

作者位次 #5/6ICML 2026Poster· Applications / Computer Vision

DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing

Kaiyang Ji · Bingsheng Qian · Binghuan Wu · Kangyi Chen · Ye Shi · Jingya Wang

多模态OpenReview

作者位次 #4/7AAAI 2026Poster· Artificial Intelligence

One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

Zeyuan Wang · Da Li · Yulin Chen · Ye Shi · Liang Bai · Tianyuan Yu · Yanwei Fu

常见合作者

JWJingya Wang×5 XTXiaoying Tang×2 YFYanwei Fu×2 MPMokai Pan×2 ZWZhongyi Wang×2 KZKaizhen Zhu×2 SDShutong Ding×2 KHKe Hu×2 ZWZhichao Wang LWLin Wang SKSai Praneeth Reddy Karimireddy YGYachen Gao