Researcher — paper.dinq.me

2026 顶会论文

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

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models

Lianyu Hu · Liqing Gao · Fanhua Shang · Liang Wan · Wei Feng

多模态OpenReview

作者位次 #5/6ICLR 2026Poster· Deep Learning / Algorithms

Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation

Jiayao Tan · Fan Lyu · Chenggong Ni · Fuyuan Hu · Wei Feng · Rui Yao

OpenReview

作者位次 #5/7ICLR 2026Poster· Computer Vision / 3D Rendering & Reconstruction

Beyond Visual Reconstruction Quality: Object Perception-aware 3D Gaussian Splatting for Autonomous Driving

Renzhi Wang · Yuxiang Fu · Wuqi Wang · Haigen Min · Wei Feng · Lei Ma · Qing Guo

多模态OpenReview

作者位次 #10/10CVPR 2026Poster· Computer Vision & Pattern Recognition

HOPS: Hierarchical Open-vocabulary Part Segmentation with Attention-Aware Filtering and Affinity-Guided Enhancement

Xinlong Li · Di Lin · Shaoyiyi Gao · Yaxuan Liu · Jixian He · Jiaxin Li · Ruonan Liu · Qing Guo · Kairui Yang · Wei Feng

多模态OpenReview 项目页

作者位次 #8/10CVPR 2026Poster· Computer Vision & Pattern Recognition

RecEdit-Drive: 3D Reconstruction-Guided Spatiotemporal Video Editing for Autonomous Driving Scenes

Yipeng Wu · Xin Wang · Chenghan Yang · Chong Wang · Dongdong Wu · Wanchao Su · Hengshuang Zhao · Wei Feng · Kairui Yang · Di Lin

多模态OpenReview 项目页

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

Towards Dynamic Modality Alignment in Multimodal Continual Learning

Jiayao Tan · Fan Lyu · Tianle Liu · Fuyuan Hu · Wei Feng

多模态对齐与偏好OpenReview 项目页

作者位次 #4/5CVPR 2026Poster· Computer Vision & Pattern Recognition

NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection

Yupeng Zhang · Ruize Han · Zhiwei Chen · Wei Feng · Liang Wan

多模态OpenReview 项目页

作者位次 #7/9CVPR 2026Poster· Computer Vision & Pattern Recognition

VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light Environment

Yanming Hui · Fanhua Shang · Hongying Liu · Ben Wang · Zhenwei Zhang · Liang Wan · Wei Feng · Tong Xue · Bingqin Lv

多模态OpenReview 项目页

作者位次 #7/9CVPR 2026Poster· Computer Vision & Pattern Recognition

Multi-modal Frequency Decomposition Network for Semantic Scene Completion

Die Zuo · Lubo Wang · Ruonan Liu · Qing Guo · Chong Wang · Dongdong Wu · Wei Feng · Kairui Yang · Di Lin

多模态OpenReview 项目页

一作AAAI 2026Poster· Artificial Intelligence

UV-RGS: Relightable 3D Gaussian Splatting from Unposed Views Under Varied Illuminations

Wei Feng · Chi Huang · Qi Zhang · Qian Zhang · Nan Li

OpenReview

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

E-Logic Prompt: Unified Energy-Logic Framework for Continual Visual Question Answering

Jiayao Tan · Tianle Liu · Fuyuan Hu · Wei Feng · Liang Wan

推理多模态检索与知识OpenReview

Wei Feng

获取完整研究档案

联系方式

2026 顶会论文

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models

Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation

Beyond Visual Reconstruction Quality: Object Perception-aware 3D Gaussian Splatting for Autonomous Driving

HOPS: Hierarchical Open-vocabulary Part Segmentation with Attention-Aware Filtering and Affinity-Guided Enhancement

RecEdit-Drive: 3D Reconstruction-Guided Spatiotemporal Video Editing for Autonomous Driving Scenes

Towards Dynamic Modality Alignment in Multimodal Continual Learning

NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection

VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light Environment

Multi-modal Frequency Decomposition Network for Semantic Scene Completion

UV-RGS: Relightable 3D Gaussian Splatting from Unposed Views Under Varied Illuminations

E-Logic Prompt: Unified Energy-Logic Framework for Continual Visual Question Answering

常见合作者