AI Foundations
Translation status
This English page provides a localized entry and navigation shell. The full article body is currently available in Chinese.
This topic hosts the more foundational and systematic material: model architectures, algorithms, mathematical foundations, multimodality, reinforcement learning, and the Hugging Face and Foundations series.
Featured reading
The Evolution of LLM Architectures Understanding Mixture-of-Experts Architectures Understanding Emergence in Large Models
Series
Article list
- Foundations 6: Between PCA and Universal Approximation
- Foundations 5: Autoencoders and PCA Equivalence
- Foundations 4: From Fourier Representation to Universal Approximation
- Foundations 3: Proving the Universal Approximation Theorem
- Foundations 2: Orthonormal Bases in Theory and Practice
- Foundations 1: Understanding FFT
- Classic Architectures and Operators in CV and Vision-Language Models
- Diffusion Models: Generative Art from Chaos to Order
- An Overview of Reinforcement Learning
- HF8: A Full-Spectrum Guide to Hugging Face
- HF7: How Hugging Face Works
- HF6: PyTorch and Transformers
- HF5: Transformers and Inference Engines
- HF4: The Role of the Transformers Library in the Hugging Face Ecosystem
- HF3: Beam Search and Sampling
- HF2: Understanding Text Generation Parameters in Transformers
- HF1: Transformers and Sentence-Transformers
- The Evolution of Computer Vision Models
- The Development of Large Model Technology
- The Evolution of Multimodal Model Architectures
- What Are Scaling Laws in Large Models?
- Hinton's Major Research Contributions and Their Impact
- The Art of Algorithm Selection
- Connectionism: From Neurons to Modern AI
- Common Traditional AI Algorithms and Deployment References
- A Quick Guide to Core AI Concepts and Key Technologies
- Understanding Emergence in Large Models
- Understanding Mixture-of-Experts Architectures
- The Evolution of LLM Architectures
- Beyond Weights: Decoding the DNA of Hugging Face Models