paper

经典论文参考

CV

计算机视觉领域的经典论文

Survey

1. A Comprehensive Survey on Source-free Domain Adaptation
2. Domain Generalization in Computational Pathology: Survey and Guidelines
3. A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
4. Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training
5. On the Design Fundamentals of Diffusion Models: A Survey

Paper

图像分类

1. AlexNet_ImageNet Classification with Deep Convolutional
2. VGGNet_Very Deep Convolutional Networks for Large-Scale Image Recognition
3. ResNet_Deep Residual Learning for Image Recognition
4. DenseNet_Densely Connected Convolutional Networks
5. ViT_An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

目标检测

6. R-CNN_Rich feature hierarchies for accurate object detection and semantic segmentation
7. Fast R-CNN
8. Mask R-CNN
9. YOLO_You Only Look Once: Unified, Real-Time Object Detection
10. DETR_End-to-End Object Detection with Transformers

语义分割

11. BiSeNet_Bilateral Segmentation Network for Real-time Semantic Segmentation
12. FCN_Fully Convolutional Networks for Semantic Segmentation
13. OCRNet_Object-Contextual Representations for Semantic Segmentation
14. U-Net_Convolutional Networks for Biomedical Image Segmentation
15. Swin Transformer_Hierarchical Vision Transformer using Shifted Windows

生成模型

NLP

自然语言处理领域的经典论文

Survey

1. Augmented Language Models: a Survey
2. Model-tuning Via Prompts Makes NLP Models Adversarially Robust
3. A Survey on In-context Learning

Paper

传统自然语言处理

1. Word2Vec_Efficient Estimation of Word Representations in Vector Space
2. CNN_Convolutional Neural Networks for Sentence Classification
3. RNN_A Critical Review of Recurrent Neural Networks for Sequence Learning
4. Seq2Seq_Sequence to Sequence Learning with Neural Networks
5. Convolutional Sequence to Sequence Learning
6. GloVe_Global Vectors for Word Representation

大模型（LLM）

1. Transformer_Attention Is All You Need
2. GPT_Improving Language Understanding by Generative Pre-Training
3. GPT2_Language Models are Unsupervised Multitask Learners
4. [GPT3_Language Models are Few-Shot Learners](2005.14165 (arxiv.org))
5. [GPT3.5_Training language models to follow instructions with human feedback](2203.02155 (arxiv.org))
6. [GPT-4 Technical Report](2303.08774 (arxiv.org))
7. BERT_Pre-training of Deep Bidirectional Transformers for Language Understanding

大模型微调

1. LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODEL
3. [The Power of Scale for Parameter-Efficient Prompt Tuning]([2104.08691] The Power of Scale for Parameter-Efficient Prompt Tuning (arxiv.org))
4. [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](2201.11903 (arxiv.org))

多模态（Multi-model Language Modal）

1. PaLM-E: An Embodied Multimodal Language Model
2. [Visual Instruction Tuning](2304.08485 (arxiv.org))
3. [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation (arxiv.org))
4. LLaRA: Aligning Large Language Models with Sequential Recommenders

RS

推荐系统领域的经典论文

Survey

1. A Survey on User Behavior Modeling in Recommender Systems
2. Disentangled Representation Learning
3. A Cookbook of Self-Supervised Learning
4. Self-Supervised Learning for Recommender Systems: A Survey
5. Graph Neural Networks in Recommender Systems: A Survey

Paper

1. Bayesian Personalized Ranking
2. Neural Collaborative Filtering
3. Neural Graph Collaborative Filtering
4. LightGCN_Simplifying and Powering Graph Convolution Network for Recommendation
5. Self-Attentive Sequential Recommendation
6. Intent-aware Ranking Ensemble for Personalized Recommendation
7. LightGT_A Light Graph Transformer for Multimedia Recommendation
8. Graph Transformer for Recommendation
9. Learning Disentangled Representations for Recommendation
10. Deep Interest Network for Click-Through Rate Prediction
11. Less is More: Reweighting Important Spectral Graph Features for Recommendation
12. Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
13. Multi-behavior Self-supervised Learning for Recommendation
14. Multi-Scenario Ranking with Adaptive Feature Learning
15. Towards Multi-Interest Pre-training with Sparse Capsule Network

Re