paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

HL

Hongsheng LI

ECCV 2026×6多模态强化学习与后训练对齐与偏好

新星分资深

16

一作贡献0

核心/参与5

方向广度6

合作网络6

0 一作 · 6 篇 · ECCV 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

6

作者位次 #5/5ECCV 2026Poster

Roam2Room: A Unified Floorplan-to-Furnished Framework for Controllable Indoor Scene Generation

Wenbo Li · Zipeng Qin · Xiaoliang Ju · Rongyao Fang · Hongsheng LI

Geometry, Localization, Matching & MotionOpenReview

作者位次 #7/7ECCV 2026Poster

ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation

Hao ZHANG · Lue Fan · Weikang Bian · Zehuan Wu · Lewei Lu · Zhaoxiang Zhang · Hongsheng LI

强化学习与后训练多模态Video Generation, Avatars & Dynamic WorldsOpenReview

作者位次 #10/10ECCV 2026Poster

VoCa: Unified Autoregressive Modeling for Talking Audio-Video Generation

Zhuofan Zong · Jiale Yuan · Yufei Liu · Dongzhi Jiang · Hao Shao · Zimu Lu · Ke Wang · Yunqiao Yang · Mingjie Zhan · Hongsheng LI

多模态Video Understanding, Generation and Multimodal LearningOpenReview

作者位次 #8/8ECCV 2026Poster

AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization

Dailan He · Guanlin Feng · Xingtong Ge · Yi ZHANG · Bingqi Ma · Guanglu Song · Yu Liu · Hongsheng LI

多模态对齐与偏好强化学习与后训练Image Generation, Editing & DiffusionOpenReview

作者位次 #8/8ECCV 2026Poster

LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving

Hao Shao · Letian Wang · Yang Zhou · Yuxuan Hu · Zhuofan Zong · Steven Waslander · Wei Zhan · Hongsheng LI

多模态Embodied AI, Robotics & Autonomous DrivingOpenReview

作者位次 #3/4ECCV 2026Poster

TimeWalker: Personalized Neural Space for Lifelong Head Avatars

Dongwei Pan · Yang Li · Hongsheng LI · Kwan-Yee Lin

对齐与偏好多模态Video Generation, Avatars & Dynamic WorldsOpenReview

常见合作者

ZZZhuofan Zong×2 HSHao Shao×2 WLWenbo Li ZQZipeng Qin XJXiaoliang Ju RFRongyao Fang HZHao ZHANG LFLue Fan WBWeikang Bian ZWZehuan Wu LLLewei Lu ZZZhaoxiang Zhang