Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Algorithms Atlas

Relationship map

Hover an algorithm to light up everything you need to learn first. Pick a route, or drag the year slider to watch 1901→2025 unfold.

223 nodes298 prerequisite linkssolid = prerequisite, dashed = related

◇ Classical Machine Learning⬡ Deep Learning Foundations◎ Transformers & Attention✳ Mixture of Experts∿ New Architectures: SSM & Linear Attention▲ Pretraining, Scaling & Distributed Training⚖ Alignment & Preference Optimization∞ Reasoning & Test-Time Compute⚙ Fine-tuning & PEFT◈ Quantization, Pruning & Distillation⚡ Inference Acceleration & Serving✦ Diffusion, Flow Matching & Generative Models◉ Multimodal & Vision⌕ RAG & Vector Retrieval⌘ Agents & Tool Use♞ Reinforcement Learning◐ World Models & Self-Supervised Learning⌬ Graph Neural Networks & AI for Science⌖ Interpretability⛨ Safety, Evaluation & Security Linear Regression Logistic Regression k-Nearest Neighbors Decision Trees (CART) Random Forest Gradient Boosting (GBDT) XGBoost LightGBM Support Vector Machine k-Means Clustering Principal Component Analysis (PCA) Expectation–Maximization (EM) t-SNE UMAP Perceptron Stochastic Gradient Descent (SGD) Backpropagation Convolutional Neural Network (CNN) Long Short-Term Memory (LSTM) Sequence-to-Sequence Learning Word2Vec Adam AdamW (Decoupled Weight Decay) Muon Optimizer Dropout Batch Normalization Layer Normalization RMSNorm Residual Networks (ResNet) GELU SwiGLU (Gated Linear Units) Byte-Pair Encoding (BPE) Tokenization Attention (Bahdanau) Transformer & Self-Attention BERT T5 (Text-to-Text Transfer Transformer) GPT-3 & In-Context Learning Rotary Position Embedding (RoPE) ALiBi (Attention with Linear Biases) Multi-Query Attention (MQA) Grouped-Query Attention (GQA) Multi-head Latent Attention (MLA) FlashAttention (v1–v3) Sliding-Window & Sparse Attention Native Sparse Attention (NSA) YaRN (Context Window Extension) Ring Attention Linear Attention Sparsely-Gated Mixture of Experts GShard (Expert Parallelism) Switch Transformer Mixtral (Top-2 MoE) DeepSeekMoE (Fine-Grained & Shared Experts) Auxiliary-Loss-Free Load Balancing Structured State Spaces (S4) Mamba (Selective State Spaces) Mamba-2 (State Space Duality) RWKV Retentive Network (RetNet) Hyena Hierarchy xLSTM Gated Delta Networks Hybrid Architectures (Jamba) Diffusion Language Models (LLaDA) Scaling Laws Chinchilla Compute-Optimal Scaling Emergent Abilities μP (Maximal Update Parametrization) Multi-Token Prediction (MTP) Mixed Precision & FP8 Training ZeRO / FSDP (Sharded Data Parallelism) Tensor Parallelism (Megatron-LM) Pipeline Parallelism (GPipe) Reinforcement Learning from Human Feedback (RLHF) Reward Modeling (Preference Learning) Direct Preference Optimization (DPO) KTO (Kahneman–Tversky Optimization) ORPO (Odds Ratio Preference Optimization) SimPO (Simple Preference Optimization) Constitutional AI / RLAIF Group Relative Policy Optimization (GRPO) RL with Verifiable Rewards (RLVR) DAPO Chain-of-Thought Prompting Self-Consistency Tree of Thoughts Process Reward Models (PRM) STaR (Self-Taught Reasoner) Test-Time Compute Scaling DeepSeek-R1 Reasoning RL Recipe Budget Forcing (s1) Instruction Tuning (FLAN) Self-Instruct Adapters Prefix & Prompt Tuning LoRA (Low-Rank Adaptation) QLoRA DoRA (Weight-Decomposed LoRA) Model Merging & Task Arithmetic Knowledge Distillation LLM.int8() & Outlier Handling GPTQ AWQ (Activation-aware Weight Quantization) SmoothQuant SparseGPT BitNet b1.58 (Ternary LLMs) KV Cache Temperature & Nucleus (Top-p) Sampling Speculative Decoding Medusa EAGLE PagedAttention (vLLM) Continuous (Iteration-Level) Batching RadixAttention (Prefix Caching) Attention Sinks (StreamingLLM) Prefill–Decode Disaggregation Variational Autoencoder (VAE) Generative Adversarial Network (GAN) VQ-VAE (Neural Discrete Representation) Denoising Diffusion Probabilistic Models (DDPM) DDIM Score-Based Models via SDEs Latent Diffusion Models Classifier-Free Guidance (CFG) Diffusion Transformer (DiT) Flow Matching Rectified Flow Consistency Models ControlNet Visual Autoregressive Modeling (VAR) Vision Transformer (ViT) CLIP (Contrastive Language–Image Pretraining) SigLIP (Sigmoid Loss) Visual Instruction Tuning (LLaVA) Flamingo Whisper Segment Anything (SAM) NeRF & 3D Gaussian Splatting Contrastive Learning (InfoNCE) BM25 Sentence Embeddings (Sentence-BERT) Dense Passage Retrieval (DPR) ColBERT (Late Interaction) HNSW (Hierarchical Navigable Small World) Product Quantization (PQ) FAISS (Billion-scale GPU Similarity Search) Matryoshka Representation Learning Retrieval-Augmented Generation (RAG) HyDE (Hypothetical Document Embeddings) GraphRAG ReAct (Reason + Act) Toolformer Function Calling / Tool Use Model Context Protocol (MCP) Reflexion Generative Agents (Memory & Reflection) Agent–Computer Interface (SWE-agent) Q-Learning Deep Q-Network (DQN) Policy Gradient (REINFORCE) Proximal Policy Optimization (PPO) Soft Actor-Critic (SAC) AlphaGo / AlphaZero (Self-Play + MCTS) MuZero World Models Dreamer (Latent Imagination) Joint-Embedding Predictive Architecture (JEPA) Genie (Generative Interactive Environments) SimCLR Masked Autoencoders (MAE) Graph Neural Networks (GCN / GAT) AlphaFold 2 AlphaGeometry (Neuro-Symbolic Reasoning) Feature Attribution (Integrated Gradients / SHAP) Grad-CAM Logit Lens & Probing Circuits & Induction Heads Superposition Sparse Autoencoders (SAE) Circuit Tracing & Attribution Graphs Locating & Editing Facts (ROME) Activation Steering Adversarial Examples (FGSM) GCG Universal Jailbreak Attack Indirect Prompt Injection Automated Red Teaming LLM-as-a-Judge LLM Watermarking Differentially Private SGD (DP-SGD) Weak-to-Strong Generalization AI Safety via Debate Sleeper Agents (Backdoors that Persist) Looped Language Models Regularized Regression (Lasso / Ridge) AdaBoost DBSCAN (Density-Based Clustering) Naive Bayes Gated Recurrent Unit (GRU) Autoencoder U-Net Weight Initialization (Xavier / He) GloVe ELMo (Contextual Word Embeddings) SentencePiece Tokenization Faster R-CNN (Object Detection) YOLO (Real-Time Object Detection) DETR (Detection Transformer) Swin Transformer DINOv2 (Self-Supervised Visual Features) Actor-Critic & A3C/A2C Trust Region Policy Optimization (TRPO) DDPG / TD3 (Continuous Control) Conservative Q-Learning (CQL, Offline RL) Decision Transformer Self-Refine Normalizing Flows (RealNVP / Glow) Connectionist Temporal Classification (CTC) wav2vec 2.0 VALL-E (Neural Codec Language Model TTS) Cross-Encoder Reranking Multi-Agent Conversation (AutoGen) MemGPT (Hierarchical Agent Memory) Membership Inference Attacks
Classical Machine LearningDeep Learning FoundationsTransformers & AttentionMixture of ExpertsNew Architectures: SSM & Linear AttentionPretraining, Scaling & Distributed TrainingAlignment & Preference OptimizationReasoning & Test-Time ComputeFine-tuning & PEFTQuantization, Pruning & DistillationInference Acceleration & ServingDiffusion, Flow Matching & Generative ModelsMultimodal & VisionRAG & Vector RetrievalAgents & Tool UseReinforcement LearningWorld Models & Self-Supervised LearningGraph Neural Networks & AI for ScienceInterpretabilitySafety, Evaluation & Security

On small screens the map is shown as a list by area.

◇ Classical Machine Learning (18)
⬡ Deep Learning Foundations (23)
◎ Transformers & Attention (18)
✳ Mixture of Experts (6)
∿ New Architectures: SSM & Linear Attention (11)
▲ Pretraining, Scaling & Distributed Training (9)
⚖ Alignment & Preference Optimization (10)
∞ Reasoning & Test-Time Compute (9)
⚙ Fine-tuning & PEFT (8)
◈ Quantization, Pruning & Distillation (7)
⚡ Inference Acceleration & Serving (10)
✦ Diffusion, Flow Matching & Generative Models (15)
◉ Multimodal & Vision (15)
⌕ RAG & Vector Retrieval (13)
⌘ Agents & Tool Use (9)
♞ Reinforcement Learning (12)
◐ World Models & Self-Supervised Learning (7)
⌬ Graph Neural Networks & AI for Science (3)
⌖ Interpretability (9)
⛨ Safety, Evaluation & Security (11)

Data updated: AI algorithms & curriculum(UTC+8)