Siying Wu — accepted AI-conference papers

2026

SEMAMIL: SEMANTIC-AWARE MULTIPLE INSTANCE LEARNING WITH RETRIEVAL-GUIDED STATE SPACE MODELING FOR WHOLE SLIDE IMAGES

Lubin Gan, Zhifeng Wang, Linhao Qu, Siying Wu, Xiaoyan Sun

ICASSP 2026poster

Multiple instance learning (MIL) has become the leading approach for extracting discriminative features from whole slide images (WSIs) in computational pathology. Attention-based MIL methods can identify key patches but tend to overlook contextual relationships. Transformer models are able to model…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Visual Perception by Large Language Model’s Weights

Feipeng Ma, Hongwei Xue, Yizhou Zhou, Guangting Wang, Fengyun Rao, Shilin Yan +4

NeurIPS 2024poster

Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs) and concatenating visual tokens with text tokens to form a unified sequence input for LLMs. These methods demonstra…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗