Researcher — paper.dinq.me

2026 顶会论文

作者位次 #6/6ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

SiMO: Single-Modality-Operable Multimodal Collaborative Perception

Jiageng Wen · Shengjie Zhao · Bing Li · Jiafeng Huang · Kenan Ye · Hao Deng

多模态OpenReview

作者位次 #4/5ACL 2026Findings· Findings of ACL

C ris P rune: Combining Contextual Relevance and Intrinsic Saliency for Efficient Visual Token Pruning in MLLM s

Ziniu Liu · Shuheng Zhou · Mingqing Liu · Hao Deng · Huijia Zhu

摘要

Visual token pruning has emerged as a pivotal strategy to alleviate the computational bottleneck in Multimodal Large Language Models (MLLMs), yet it frequently compromises the integrity of visual understanding in pursuit of efficiency. Existing methods face a fundamental tension: vision-centric a...

多模态效率与系统对齐与偏好OpenReview 项目页

作者位次 #5/6KDD 2026Oral· Knowledge Discovery & Data Mining

Invariant Structure Learning with Pre-trained Language Models for Spatio-temporal Graph

Ting Wang · Duo Zhou · Daqian Shi · Hao Tang · Hao Deng · Shengjie Zhao

数据与预训练检索与知识OpenReview

Hao Deng

获取完整研究档案

联系方式

2026 顶会论文

SiMO: Single-Modality-Operable Multimodal Collaborative Perception

C ris P rune: Combining Contextual Relevance and Intrinsic Saliency for Efficient Visual Token Pruning in MLLM s

Invariant Structure Learning with Pre-trained Language Models for Spatio-temporal Graph

常见合作者