Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/6ICML 2026Poster· Deep Learning / Large Language Models

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling

Xianjie Liu · Yiman Hu · Yixiong Zou · Liang Wu · Jian Xu · Bo Zheng

OpenReview

作者位次 #2/4ICML 2026Poster· Deep Learning / Large Language Models

Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation

Yuhan Liu · Yixiong Zou · Yuhua Li · Ruixuan Li

效率与系统OpenReview

作者位次 #2/4ICML 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning

Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning

Shuai Yi · Yixiong Zou · Yuhua Li · Ruixuan Li

对齐与偏好OpenReview

作者位次 #5/7ICML 2026Poster· Deep Learning / Large Language Models

E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs

Xianjie Liu · Yiman Hu · Liang Wu · Ping Hu · Yixiong Zou · Jian Xu · Bo Zheng

多模态评测与基准OpenReview

作者位次 #2/4CVPR 2026Poster· Computer Vision & Pattern Recognition

Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning

Shuai Yi · Yixiong Zou · Yuhua Li · Ruixuan Li

多模态OpenReview 项目页

作者位次 #2/4CVPR 2026Poster· Computer Vision & Pattern Recognition

Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection

Yongwei Jiang · Yixiong Zou · Yuhua Li · Ruixuan Li

多模态OpenReview 项目页

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

Is Bin Generation Indispensable? A Bin-Generation-Free Dataset Quantization via Semantic Perspective

Maijie Deng · Yuhua Li · Yixiong Zou · Yao Wu · Chenru Ma

多模态效率与系统数据与预训练OpenReview 项目页

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

Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning

Zhenyu Zhang · Guangyao Chen · Yixiong Zou · Yuhua Li · Ruixuan Li

多模态OpenReview 项目页

作者位次 #2/5CVPR 2026Poster· Computer Vision & Pattern Recognition

Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning

Zhenyu Zhang · Yixiong Zou · Yuhua Li · Ruixuan Li · Guangyao Chen

多模态OpenReview 项目页

作者位次 #2/4CVPR 2026Poster· Computer Vision & Pattern Recognition

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment

Yaze Zhao · Yixiong Zou · Yuhua Li · Ruixuan Li

对齐与偏好可解释性多模态OpenReview 项目页

作者位次 #5/6AAAI 2026Poster· Artificial Intelligence

Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning

Liqin Luo · Guangyao Chen · Xiawu Zheng · Yongxing Dai · Yixiong Zou · Yonghong Tian

推理智能体与工具多模态OpenReview

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

Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding

Qingyang Yan · Guangyao Chen · Yixiong Zou

多模态强化学习与后训练OpenReview

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

Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning

Zhenyu Zhang · Guangyao Chen · Yixiong Zou · Zhimeng Huang · Yuhua Li

社会与人本OpenReview

Yixiong Zou

获取完整研究档案

联系方式

2026 顶会论文

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling

Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation

Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning

E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs

Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning

Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection

Is Bin Generation Indispensable? A Bin-Generation-Free Dataset Quantization via Semantic Perspective

Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning

Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment

Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning

Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding

Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning

常见合作者