Aoqi Wu — accepted AI-conference papers

2026

D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning

Evelyn Zhang, Fufu Yu, Aoqi Wu, Zichen Wen, Ke Yan, Shouhong Ding +2

AAAI 2026technical

Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we find that current methods, while adequate for general understanding, catastrophically fail on fine-grained localization t

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation

Weiquan Huang, Aoqi Wu, Yifan Yang, Xufang Luo, Yuqing Yang, Usman Naseem +7

AAAI 2026technical

CLIP is a seminal multimodal model that maps images and text into a shared representation space by contrastive learning on billions of image–caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate how the superior linguistic understanding and broad world knowled

Cited by 0 Source ↗PDF ↗Scholar ↗