paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

YT

Yansong Tang

IROS 2026×3ICRA 2026×2CVPR 2026ICML 2026多模态强化学习与后训练推理检索与知识理论与学习动力学

新星分资深

41

一作贡献0

核心/参与33

方向广度19

合作网络12

0 一作 · 7 篇 · IROS 2026 / ICRA 2026 / CVPR 2026 / ICML 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 #8/10ICML 2026Poster· Applications / Computer Vision

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

Yiyang Fu · Chubin Zhang · Shukai Gong · Yufan Deng · Kaiwei Sun · Qiyang Min · Qibin Hou · Yansong Tang · Jianan Wang · Zhou Daquan

多模态OpenReview

作者位次 #10/10CVPR 2026Poster· Computer Vision & Pattern Recognition

Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning

Haoji Zhang · Xin Gu · Jiawen Li · Chixiang Ma · Sule Bai · Chubin Zhang · Bowen Zhang · Zhichao Zhou · Dongliang He · Yansong Tang

多模态推理强化学习与后训练OpenReview 项目页

作者位次 #5/7ICRA 2026Oral· Robotics & Automation

DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation

Yue Su · Chubin Zhang · Sijin Chen · Liufan Tan · Yansong Tang · Jianan Wang · Xihui Liu

理论与学习动力学OpenReview

作者位次 #5/6ICRA 2026Oral· Robotics & Automation

VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search

Wenkai Guo · Guanxing Lu · Haoyuan Deng · Zhenyu Wu · Yansong Tang · Ziwei Wang

推理多模态检索与知识OpenReview

作者位次 #5/5IROS 2026Poster· Making Reinforcement Learning Practical for Manipulation

Human-In-The-Loop Online Rejection Sampling for Robotic Manipulation

Guanxing Lu · Rui Zhao · Haitao Lin · He Zhang · Yansong Tang

强化学习与后训练检索与知识社会与人本Reinforcement LearningDeep Learning in Grasping and ManipulationHuman Factors and Human-in-the-LoopOpenReview

作者位次 #7/8IROS 2026Poster· Scaling Up Robot Policy Learning

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning

Guanxing Lu · Wenkai Guo · Chubin Zhang · Yuheng Zhou · Haonan Jiang · Zifeng Gao · Yansong Tang · Ziwei Wang

强化学习与后训练Reinforcement LearningDeep Learning in Grasping and ManipulationOpenReview

作者位次 #4/5IROS 2026Poster· Generative and Predictive Models for Robot Behavior

RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation

Chuanrui Zhang · ZhengXian Wu · Guanxing Lu · Yansong Tang · Ziwei Wang

多模态Deep Learning for Visual PerceptionDeep Learning MethodsImitation LearningOpenReview

常见合作者

CZChubin Zhang×4 GLGuanxing Lu×4 JWJianan Wang×2 WGWenkai Guo×2 ZWZiwei Wang×2 YFYiyang Fu SGShukai Gong YDYufan Deng KSKaiwei Sun QMQiyang Min QHQibin Hou ZDZhou Daquan