Blog

Articles organised by topic.

Browse the VenusAI Lab article library by category and tag: AI foundations, deep learning, graph neural networks, multimodal models and practical projects.

VenusAI Lab
Libraryholographic index
Deep Learning 41 articles Transformer Example articlesSimAMSANetSwin TransformerPyramid Vision TransformerAttentional Feature Fusion Graph Neural Networks 22 articles Graph Neural NetworksDeep Learning Example articlesGraphGANDeep Graph InfomaxRelational Graph Convolutional Neural NetworkResidual Gated Graph ConvnetsGraph Isomorphism Network Geometric Graph Neural Networks 13 articles Deep LearningGraph Neural Networks Example articlesSE(3)-TransformersSEGNNTensor Field Networks (TFN)LEFTNetClofNet Training and Optimization 13 articles Deep Learning Example articlesTutorial 11 – Active LearningTutorial 10 – Reinforcement LearningUnderfitting, Overfitting, and RegularizationOptimization Algorithms and OptimizersTutorial 09 – Federated Learning Plug-and-Play Modules 11 articles Transformer Example articlesSimAMSANetSwin TransformerPyramid Vision TransformerAttentional Feature Fusion Algorithms and Frameworks 10 articles Deep Learningpython Example articlesEvolution of Attention (MHA, MQA, GQA, MLA)Reinforcement Learning (DRL)Graph Neural Networks (GNN)Diffusion Models (DDPM)Generative Adversarial Networks (GAN) Classic Graph Neural Networks 9 articles Graph Neural NetworksDeep Learning Example articlesGraphGANDeep Graph InfomaxRelational Graph Convolutional Neural NetworkResidual Gated Graph ConvnetsGraph Isomorphism Network Multimodal Algorithms 9 articles Example articlesPaLI Multimodal Model Series: Pathways Language and Image ModelUni-Perceiver Series: A Dual-Encoder-Based Unified Multimodal ModelBEiT: An Early Look at a Unified Multimodal FrameworkCoCa: The All-Rounder of Multimodal LearningBLIP: Bootstrapped Data Cleaning for Multimodal Learning News 9 articles Example articlesWeekly AI News: July 21–27, 2026Weekly AI News: July 14–20, 2026Weekly AI News: July 7–13, 2026Weekly AI News: June 30–July 6, 2026Weekly AI News: June 23–29, 2026 AI Mathematics 7 articles Advanced Mathematicspython Example articlesQuantum MechanicsGroup TheoryGraph TheoryInformation TheoryProbability and Statistics
Learning paths

Browse by learning path, not by a flat post list.

The library is organised into readable, progressive learning paths based on the structure of deep learning foundations: mathematics, algorithms and training.

Suggested order: start with mathematical foundations, move into model architectures, then study training methods. If you already have a clear direction, jump directly to the GNN or multimodal tracks.

Part 01

Math Foundations

Build the mathematical base for deep learning: calculus, linear algebra, probability, information theory and geometric structures.

01Advanced MathematicsJul 16, 2024Advanced Mathematicspython02Linear AlgebraJul 17, 202403Probability and StatisticsJul 25, 202404Information TheoryJul 26, 202405Graph TheoryJul 26, 202406Group TheoryJul 27, 202407Quantum MechanicsJul 27, 2024
Part 02

Deep Learning Models

Follow the model roadmap from NN, CNN and RNN to Transformer, GAN, Diffusion, GNN and RL.

01Neural Networks (NN)Jul 29, 202402Convolutional Neural Networks (CNN)Jul 31, 2024Deep Learningpython03Recurrent Neural Networks (RNN)Sep 13, 2024Deep Learning04Encoder-Decoder ArchitecturesSep 14, 2024Deep Learning05Self-Attention Mechanisms and Transformer AlgorithmsSep 18, 2024Deep Learning06Generative Adversarial Networks (GAN)Sep 19, 2024Deep Learning07Diffusion Models (DDPM)Sep 23, 2024Deep Learning08Graph Neural Networks (GNN)Sep 26, 2024Deep Learning09Reinforcement Learning (DRL)Sep 26, 2024Deep Learning
Part 03

Model Training Methods

Training paradigms: supervised, unsupervised, self-supervised, semi-supervised, contrastive, transfer, adversarial, ensemble, federated and active learning.

01Tutorial 01 – Supervised LearningJan 20, 202502Tutorial 02 – Seeing the Big Picture from Small Clues: Unsupervised LearningJan 24, 202503Tutorial 03 – Learning Without a Teacher: Self-supervised LearningJan 24, 202504Tutorial 04 – From a Few Points to the Whole Picture: Semi-supervised LearningJan 25, 202505Tutorial 05 – Distinguishing Similarities and Differences: Contrastive LearningJan 25, 202506Tutorial 06 – Learning by Transfer: Transfer LearningJan 25, 202507Tutorial 07 – Learning Through Competition: Adversarial LearningJan 25, 202508Tutorial 08 – Strength in Numbers: Ensemble LearningJan 25, 202509Tutorial 09 – Federated LearningJan 25, 202510Tutorial 10 – Reinforcement LearningApr 19, 202511Tutorial 11 – Active LearningApr 19, 2025

Advanced Graph Neural Networks

For deeper study of GNNs, geometric deep learning and molecular modelling.

01Graph Convolutional Network（GCN）Oct 9, 2024Deep LearningGraph Neural Networks02Graph Sample and Aggregate Network（GraphSAGE）Oct 10, 2024Graph Neural Networks03Graph Attention Network（GAT）Oct 10, 2024Graph Neural Networks04EGNNDec 3, 202405PAINNDec 26, 202406GVP-GNNDec 27, 202407LEFTNetDec 28, 202408Tensor Field Networks (TFN)Dec 28, 202409SEGNNJan 6, 2025Deep LearningGraph Neural Networks10SE(3)-TransformersJan 6, 2025Deep LearningGraph Neural Networks

Multimodal and Vision Models

From CLIP and ALBEF to BLIP, CoCa, BEiT, VLMO and vision Transformers.

01CLIP: Contrastive Language-Image Pre-TrainingApr 21, 202502ALBEF (Align Before Fuse): Modality Alignment and Knowledge DistillationApr 25, 202503VLMO: A Vision-Language Model Based on Mixture-of-ExpertsApr 27, 202504BLIP: Bootstrapped Data Cleaning for Multimodal LearningApr 28, 202505CoCa: The All-Rounder of Multimodal LearningApr 29, 202506BEiT: An Early Look at a Unified Multimodal FrameworkMay 9, 202507Uni-Perceiver Series: A Dual-Encoder-Based Unified Multimodal ModelMay 14, 202508PaLI Multimodal Model Series: Pathways Language and Image ModelMay 23, 202509SENet：Squeeze-and-Excitation NetworksJul 9, 202510Swin TransformerJul 16, 2025Transformer
Scroll to Top