paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

DL

Dingkang Liang

CVPR 2026×4ICLR 2026×2AAAI 2026ICRA 2026多模态推理代码强化学习与后训练效率与系统

新星分新星

92

一作贡献80

核心/参与32

方向广度19

合作网络9

2 一作 · 8 篇 · CVPR 2026 / ICLR 2026 / AAAI 2026 / ICRA 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 #3/9ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding

Yiran Guan · Sifan Tu · Dingkang Liang · Linghao Zhu · Jianzhong Ju · Zhenbo Luo · Jian Luan · Yuliang Liu · Xiang Bai

多模态推理代码OpenReview

作者位次 #3/9ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle

Linghao Zhu · Yiran Guan · Dingkang Liang · Jianzhong Ju · Zhenbo Luo · Bin Qin · Jian Luan · Yuliang Liu · Xiang Bai

多模态强化学习与后训练效率与系统OpenReview

作者位次 #6/7CVPR 2026Poster· Computer Vision & Pattern Recognition

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

Zhengyang Sun · Yu Chen · Xin Zhou · Xiaofan Li · Xiwu Chen · Dingkang Liang · Xiang Bai

多模态对齐与偏好OpenReview 项目页

作者位次 #9/9CVPR 2026Poster· Computer Vision & Pattern Recognition

FVAR: Next-Focus Prediction for Visual Autoregressive Modeling

Xiaofan Li · Chenming Wu · Yanpeng Sun · Jiaming Zhou · Delin Qu · Yansong Qu · Weihao Bo · Haibao Yu · Dingkang Liang

多模态OpenReview 项目页

作者位次 #2/8CVPR 2026Poster· Computer Vision & Pattern Recognition

OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models

Xingkui Zhu · Dingkang Liang · Cheng Chen · Daoxin Zhang · lv Hanxiang · Zhe Xu · Yao Hu · Xiang Bai

多模态OpenReview 项目页

作者位次 #5/6CVPR 2026Poster· Computer Vision & Pattern Recognition

PointTPA: Dynamic Network Parameter Adaptation for 3D Scene Understanding

Siyuan Liu · Chaoqun Zheng · Xin Zhou · Tianrui Feng · Dingkang Liang · Xiang Bai

多模态OpenReview 项目页

一作ICRA 2026Oral· Robotics & Automation

UniFuture: A 4D Driving World Model for Future Generation and Perception

Dingkang Liang · Dingyuan Zhang · Xin Zhou · Sifan Tu · Tianrui Feng · Xiaofan Li · Yumeng Zhang · Mingyang Du · Xiao Tan · Xiang Bai

一作AAAI 2026Poster· Artificial Intelligence

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution

Dingkang Liang · Cheng Zhang · Xiaopeng Xu · Jianzhong Ju · Zhenbo Luo · Xiang Bai

智能体与工具OpenReview

常见合作者

XBXiang Bai×7 JJJianzhong Ju×3 ZLZhenbo Luo×3 XZXin Zhou×3 YGYiran Guan×2 STSifan Tu×2 LZLinghao Zhu×2 JLJian Luan×2 YLYuliang Liu×2 XLXiaofan Li×2 TFTianrui Feng×2 BQBin Qin