paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

JH

Junhui Hou

ECCV 2026×6多模态强化学习与后训练效率与系统可解释性

新星分资深

25

一作贡献0

核心/参与15

方向广度8

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

MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes

Ye Tao · Yuxin Yao · Kendong Liu · Dapeng Wu · Junhui Hou

多模态Video Generation, Avatars & Dynamic WorldsOpenReview

作者位次 #5/5ECCV 2026Poster

REFINE: Super-efficient Pruning for 3D Gaussian Splatting via Rendering-Free Primitive Importance

Zhang Chen · Shuai Wan · Mengting Yu · Fuzheng Yang · Junhui Hou

效率与系统3D Reconstruction, Gaussian Splatting & Neural RenderingOpenReview

作者位次 #6/7ECCV 2026Poster

Fragmented Text Is Insufficient for Image Representation: Fine-Grained Correspondence in Multimodal Dataset Distillation

Jingwei Fang · Yaxin Hou · Bo Han · Xu Zhang · Hui LIU · Junhui Hou · Yuheng Jia

多模态可解释性强化学习与后训练Open-World Recognition, Segmentation & TransferOpenReview

作者位次 #3/4ECCV 2026Poster

SOVTrack: Open-Vocabulary Multi-Object Tracking with Self-Supervised Pseudo Labeling and Feature Distillation

Zekun QIAN · Ruize Han · Junhui Hou · Wei Feng

强化学习与后训练Open-World Recognition, Segmentation & TransferOpenReview

作者位次 #3/3ECCV 2026Poster

Diffusion Image Generation with Explicitly Modeling of Data Manifold Geometry

Duoduo Xue · Zhiyu Zhu · Junhui Hou

多模态Low-Level Vision, Restoration & Generative PriorsOpenReview

作者位次 #8/11ECCV 2026Poster

Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens

Ziran Qin · Youru Lv · Mingbao Lin · Zeren Zhang · chaofan gan · Tieyuan Chen · Liquan Shen · Junhui Hou · Chern Hong Lim · Fei Wen · Weiyao Lin

多模态Video Understanding, Generation and Multimodal LearningOpenReview

常见合作者

YTYe Tao YYYuxin Yao KLKendong Liu DWDapeng Wu ZCZhang Chen SWShuai Wan MYMengting Yu FYFuzheng Yang JFJingwei Fang YHYaxin Hou BHBo Han XZXu Zhang