[[MachineLearning/NLP/GNN/GraphToekn/GraphToken.pdf|GraphToken]]

[[GNN-RAG.pdf|GNN-RAG]]

[[MachineLearning/NLP/RAG/G-Retriever/G-Retriever.pdf|G-Retriever]]

生成网络评价指标

[[MachineLearning/NLP/预训练大模型/Agent/MMedAgentg.pdf|MMedAgentg]]

[[MachineLearning/多模态/MLLM/BiomedParse/BiomedParse.pdf|BiomedParse]]

通道空间和像素注意力

[[MachineLearning/NLP/预训练大模型/LLaMA/Vicuna.pdf|Vicuna]]

[[EVE.pdf|EVE]]

大模型扫盲

Normalizaiton

大模型词表

自注意力机制中的掩码生成

[[Vitron.pdf|Vitron]]

OFA-达摩院多模态模型

Achieving Cross Modal Generalization with Multimodal Unified Representation

Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion

Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models

Predictive Dynamic Fusion

DilateFormer:Multi-Scale Dilated Transformer for Visual Recognition

M2SNet:Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

基于变形detr和多层次特征融合的精确白细胞检测，以辅助血液疾病的诊断

Cascade Fusion Network for Dense Prediction

Pyraformer

基于多尺度特征提取的时间序列预测

混合专家模型

Prov-GigaPath

OpenGan

VAE

UNI

GAN

Swin-Transformer

ViT

AttentionIsAllYouNeed

SimCLR2

SimCLR

[[StableDiffusion3.pdf|StableDiffusion3]]

Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning