Researcher — paper.dinq.me

2026 顶会论文

作者位次 #12/15ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

Zhenxin Lei · Zhangwei Gao · Changyao Tian · Erfei Cui · Guanzhou Chen · Danni Yang · Yuchen Duan · Zhaokai Wang · Wenhao Li · Weiyun Wang · Xiangyu Zhao · Jiayi Ji · Yu Qiao · Wenhai Wang · Gen Luo

多模态OpenReview

作者位次 #6/11ICLR 2026Poster· Computer Vision / Image and Video Generation

JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization

Kai Liu · Wei Li · Lai Chen · Shengqiong Wu · Yanhao Zheng · Jiayi Ji · Fan Zhou · Jiebo Luo · Ziwei Liu · Hao (Scofield) Fei · Tat-Seng Chua

多模态OpenReview

作者位次 #5/7ICLR 2026Poster

FastVGGT: Fast Visual Geometry Transformer

You Shen · Zhipeng Zhang · Yansong Qu · Xiawu Zheng · Jiayi Ji · Shengchuan Zhang · Liujuan Cao

多模态OpenReview

作者位次 #10/16ICLR 2026Poster· Computer Vision / Image and Video Generation

RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

Mingrui Wu · Lu Wang · Pu Zhao · Fangkai Yang · Jianjin Zhang · Jianfeng Liu · Yuefeng Zhan · Weihao Han · Hao Sun · Jiayi Ji · Xiaoshuai Sun · Qingwei Lin · Weiwei Deng · Dongmei Zhang · Feng Sun · Rongrong Ji

多模态推理强化学习与后训练OpenReview

作者位次 #7/11ICLR 2026Poster

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

Ziyang Gong · Wenhao Li · Xianzheng Ma · Songyuan Li · Zhaokai Wang · Songze Li · Jiayi Ji · Xue Yang · Gen Luo · Junchi Yan · Rongrong Ji

多模态评测与基准长上下文与架构OpenReview

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

CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic Scanning

Yubin Gu · Boyang Hou · Yuan Meng · Wenting Luo · Jiayi Ji · Xiaoshuai Sun

多模态OpenReview 项目页

作者位次 #6/8CVPR 2026Poster· Computer Vision & Pattern Recognition

Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding

Wang Chen · Yuhui Zeng · Yongdong Luo · Tianyu Xie · Luojun Lin · Jiayi Ji · Yan Zhang · Xiawu Zheng

多模态OpenReview 项目页

作者位次 #3/8CVPR 2026Poster· Computer Vision & Pattern Recognition

MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

Changli Wu · Haodong Wang · Jiayi Ji · Yutian Yao · Chunsai Du · Jihua Kang · Yanwei Fu · Liujuan Cao

多模态OpenReview 项目页

作者位次 #3/5CVPR 2026Poster· Computer Vision & Pattern Recognition

MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models

Mingrui Wu · Hang Liu · Jiayi Ji · Xiaoshuai Sun · Rongrong Ji

多模态评测与基准OpenReview 项目页

作者位次 #5/7CVPR 2026Spotlight· Computer Vision & Pattern Recognition

PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation

Shuyan Ke · Yifan Mei · Changli Wu · Yonghan Zheng · Jiayi Ji · Liujuan Cao · Rongrong Ji

多模态推理OpenReview 项目页

作者位次 #7/10ACL 2026Findings· Findings of ACL

CSMCIR : C o T -Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval

Zhipeng Qian · Zihan Liang · Yufei Ma · Ben Chen · Huangyu Dai · Yiwei Ma · Jiayi Ji · Chenyi Lei · Han Li · Xiaoshuai Sun

摘要

Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text, offering substantial advantages over single-modality retrieval systems. However, existing CIR methods suffer from representation space fragmentation: queries and targets co...

多模态检索与知识推理OpenReview 项目页

作者位次 #3/7AAAI 2026Poster· Artificial Intelligence

Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach

Lvpan Cai · Haowei Wang · Jiayi Ji · YanShu ZhouMen · Shen Chen · Taiping Yao · Xiaoshuai Sun

多模态数据与预训练OpenReview

作者位次 #3/5AAAI 2026Poster· Artificial Intelligence

3D-DRES: Detailed 3D Referring Expression Segmentation

Qi Chen · Changli Wu · Jiayi Ji · Yiwei Ma · Liujuan Cao

OpenReview

作者位次 #6/6AAAI 2026Poster· Artificial Intelligence

FIND: A Simple Yet Effective Baseline for Diffusion-Generated Image Detection

Jie Li · Yingying Feng · Chi Xie · Jie Hu · Lei Tan · Jiayi Ji

多模态OpenReview

作者位次 #8/10AAAI 2026Poster· Artificial Intelligence

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension

Yongdong Luo · Wang Chen · Weizhong Huang · Shukang Yin · Haojia Lin · Jinfa Huang · Chaoyou Fu · Jiayi Ji · Xiawu Zheng · Jiebo Luo

推理多模态OpenReview

Jiayi Ji

获取完整研究档案

联系方式

2026 顶会论文

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization

FastVGGT: Fast Visual Geometry Transformer

RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic Scanning

Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding

MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models

PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation

CSMCIR : C o T -Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval

Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach

3D-DRES: Detailed 3D Referring Expression Segmentation

FIND: A Simple Yet Effective Baseline for Diffusion-Generated Image Detection

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension

常见合作者