Multimodal

ALBEF

Blip

VLMo

ViLT

TART

More >>

blogs

Hello World

hexo结合Github搭建自己的博客

保证连接上github

MindSpore训练模型

MindSpore从大型模型中导出模块以及权重处理

More >>

DeepLearning

Dropout

上采样(UpSampling)与下采样(DownSampling)

GELU

CV

All in Tokens Unifying Output Space of Visual Tasks via Soft Token

ViT

Swin Transformer

Swin Transformer V2

Yolo_World

LLM

BERT

self-instruct

Speculating LLMs Chinese Training Data Pollution from Their Tokens

fine-tuning

Blip-fine-tuning

Attack

BertAttack

VQAttack

SSP.md

FDA

m

Recommendation

Multimodal Pre-training for Sequential Recommendation via Contrastive Learning

AlignRec：Aligning and Training in Multimodal Recommendations

Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation

How Can Recommender Systems Benefit from Large Language Models: A Survey

Recommender Systems with Generative Retrieval

More >>

Multimodal_Agent

CRAFT: CUSTOMIZING LLMS BY CREATING AND RETRIEVING FROM SPECIALIZED TOOLSETS

Multimodal Agent

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Jailbreak Defence

Steering Llama 2 via Contrastive Activation Addition

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks