Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/5ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

Qing Jiang · Xingyu Chen · Zhaoyang Zeng · Junzhi Yu · Lei Zhang

推理多模态OpenReview

作者位次 #6/6ICLR 2026Poster· Computer Vision / Everything Else

TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video

Jinyuan Qu · Hongyang Li · Shilong Liu · Tianhe Ren · Zhaoyang Zeng · Lei Zhang

多模态OpenReview

作者位次 #3/3ICLR 2026Poster· Computer Vision / Segmentation

OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction

Hongyang Li · Jinyuan Qu · Lei Zhang

多模态OpenReview

作者位次 #9/10ICLR 2026Poster· Computer Vision / Image and Video Generation

Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

Zixin Yin · Xili Dai · Ling-Hao Chen · Deyu Zhou · Jianan Wang · Duomin Wang · Gang Yu · Lionel Ni · Lei Zhang · Heung-Yeung Shum

多模态OpenReview

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

Detect Anything via Next Point Prediction

Qing Jiang · Junan Huo · Xingyu Chen · Yuda Xiong · Zhaoyang Zeng · Yihao Chen · Tianhe Ren · Junzhi Yu · Lei Zhang

多模态OpenReview 项目页

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

SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model

Yukai Shi · Weiyu Li · Zihao Wang · Hongyang Li · Xingyu Chen · Ping Tan · Lei Zhang

多模态OpenReview 项目页

作者位次 #8/8AAAI 2026Poster· Artificial Intelligence

SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features

Jinyuan Qu · Hongyang Li · Xingyu Chen · Shilong Liu · Yukai Shi · Tianhe Ren · Ruitao Jing · Lei Zhang

多模态OpenReview

作者位次 #9/10AAAI 2026Poster· Artificial Intelligence

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

Jiaqi Tang · Jianmin Chen · Wei Wei · Xiaogang Xu · Runtao Liu · Xiangyu Wu · Qipeng Xie · Jiafei Wu · Lei Zhang · Qifeng Chen

推理多模态OpenReview

作者位次 #7/7AAAI 2026Poster· Artificial Intelligence

T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object Detection

Jiazhou Zhou · Qing Jiang · Kanghao Chen · Lutao Jiang · Yuanhuiyi Lyu · Ying-Cong Chen · Lei Zhang

多模态OpenReview

作者位次 #4/5AAAI 2026Poster· Artificial Intelligence

Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning

Jiayi Lin · Yanlin Wang · Yibiao Yang · Lei Zhang · Yutao Xie

代码OpenReview

Lei Zhang

获取完整研究档案

联系方式

2026 顶会论文

Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning

TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video

OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction

Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

Detect Anything via Next Point Prediction

SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model

SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object Detection

Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning

常见合作者