paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

YL

Yichen Li

NeurIPS 2026×10智能体与工具强化学习与后训练对齐与偏好社会与人本安全

新星分贡献者

82

一作贡献0

核心/参与71

方向广度10

合作网络12

0 一作 · 10 篇 · NeurIPS 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

10

作者位次 #2/7NeurIPS 2026Poster

Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM Training

Qiyu Qin · Yichen Li · Haozhao Wang · Tianzhe Xiao · Hao Zhou · Imran Razzak · Ruixuan Li

智能体与工具效率与系统OpenReview

作者位次 #5/8NeurIPS 2026Poster

SeaPilot: Mobile Agent with Self-refining Environment Alignment

Zhigang Zuo · Senyao Li · Yufeng Jiang · Haozhao Wang · Yichen Li · Wenchao Xu · Jingcai Guo · Ruixuan Li

智能体与工具对齐与偏好OpenReview

作者位次 #4/8NeurIPS 2026Poster

FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation

Haitao Wang · Haozhao Wang · Wenchao Xu · Yichen Li · Xiaoquan Yi · Tianzhe Xiao · Jingcai Guo · Ruixuan Li

强化学习与后训练OpenReview

作者位次 #3/9NeurIPS 2026Poster

VERITAS: Veracity-Enhanced Robust Identification of LLM-generated Text Against Style-shifts

Xiaoquan Yi · Haozhao Wang · Yichen Li · Wenchao Xu · Jinghua Zhang · Yuhua Li · Rui Zhang · Imran Razzak · Ruixuan Li

作者位次 #8/11NeurIPS 2026Poster· Applications / Health

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory

Haoran Sun · Wenjie Li · Yujie Zhang · Zekai Lin · Fanrui Zhang · Kaitao Chen · Xingqi He · Yichen Li · Mianxin Liu · Lei Liu · Yankai Jiang

社会与人本推理智能体与工具OpenReview

作者位次 #2/7NeurIPS 2026Poster

Rehearsal-Free Statistical Prototype Regularization for Federated Incremental Learning

Xiuying Wang · Yichen Li · Jiahua Cheng · Xiwei Liu · Chuang Zhao · Bo Liu · Imran Razzak

作者位次 #2/7NeurIPS 2026Poster

Heterogeneity-aware Distillation for Federated Continual Learning

Gaozhuo Liu · Yichen Li · Xiuying Wang · Yulong Li · Chuang Zhao · Yankai Jiang · Imran Razzak

强化学习与后训练OpenReview

作者位次 #3/6NeurIPS 2026Poster

FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning

Tianzhe Xiao · Haozhao Wang · Yichen Li · Qiyu Qin · Debin Liu · Ruixuan Li

安全OpenReview

作者位次 #3/7NeurIPS 2026Poster

Personalized Safety in Federated Fine-Tuning of Large Language Models

Tianzhe Xiao · Gaozhuo Liu · Yichen Li · Haozhao Wang · Hanlin Cai · Ruixuan Li · Ozgur Akan

对齐与偏好安全强化学习与后训练OpenReview

作者位次 #6/11NeurIPS 2026Poster

DoAtlas-1: A Causal Compilation Paradigm for Clinical AI

Yulong Li · Jianxu Chen · Xiwei Liu · Chuanyue Suo · Rong Xia · Yichen Li · Xinlin Zhuang · Niranjana A Menon · Jionglong Su · Eran Segal · Imran Razzak

社会与人本OpenReview

常见合作者

HWHaozhao Wang×6 RLRuixuan Li×6 IRImran Razzak×5 TXTianzhe Xiao×4 WXWenchao Xu×3 QQQiyu Qin×2 JGJingcai Guo×2 XYXiaoquan Yi×2 YJYankai Jiang×2 XWXiuying Wang×2 XLXiwei Liu×2 CZChuang Zhao×2