Search

[AI]

•
AI 모델과 관련 내용 위주로 정리

Variational Auto Encoder(VAE)

AI/ Variational Auto Encoder(VAE)
AI/ Dimension Reduction - PCA, FA, Autoencoder, Multi-Dimensional Scaling(MDS)
AI/ Variational Inference
AI/ Reparameterization Trick
AI/ Control Variate
AI/ Mean Field Approximation(MFA)
AI/ Convolution

Normalizing Flow

AI/ Normalizing Flow
AI/ Article/ Flow-based Deep Generative Models
AI/ Change of Variables

Energy-Based Models

AI/ Energy-Based Model(EBM)
AI/ Contrastive Divergence(CD)
AI/ Score Matching(SM)
AI/ Boltzmann Machine, Restricted Boltzmann Machine(RBM)
AI/ Metropolis-Hastings Algorithm
AI/ Gibbs Distribution, Gibbs Sampling
AI/ Importance Sampling, Annealed Importance Sampling(AIS)
AI/ Hamiltonian Mechanics, Hamiltonian Monte Carlo(HMC)
AI/ Langevin Dynamics, Langevin Monte Carlo(LMC)

Diffusion Model

AI/ Denoising Diffusion Probabilistic Model(DDPM)
AI/ Paper/ Denoising Diffusion Probabilistic Models
AI/ Article/ Generative Modeling by Estimating Gradients of the Data Distribution
AI/ Article/ What are Diffusion Models
AI/ Article/ The Annotated Diffusion Model
AI/ Hierarchical VAE(H-VAE)
AI/ Score Based Generative Model(SGM)
AI/ Stochastic Differential Equation(SDE), Ordinary Differential Equation(ODE)
AI/ Denoising Diffusion Implicit Model(DDIM)
AI/ Progressive Distillation
AI/ U-Net
AI/ Latent Diffusion Model(LDM)
AI/ Conditional Model
AI/ unCLIP
AI/ ControlNet
AI/ Super Resolution, Noise Conditioning Augmentation(NCA)
AI/ Diffusion Transformer(DiT)
AI/ Discrete DDPM(D3PM)

Consistency Model

AI/ Consistency Model
AI/ Paper/ Consistency Model
AI/ Paper/ Consistency Model/ Appendix
AI/ Lipschitz Constant
AI/ Euler Method(Euler Solver)
AI/ Heun Method(Heun Solver)

Generative Adversary Network

AI/ Generative Adversarial Network(GAN)
AI/ GAN Objective
AI/ f-divergence

Long-Short Term Memory(LSTM)

AI/ Long-Short Term Memory(LSTM)
AI/ Recurrent Neural Network(RNN)
AI/ Markov Models, Hidden Markov Models(HMM)
AI/ State Space Model(SSM)
AI/ Linear Dynamical System(LDS)

Transformer

AI/ Transformer
AI/ Paper/ Attention Is All You Need
AI/ Article/ Annotated Transformer
AI/ Attention
AI/ Multiplicative Interaction
AI/ Embedding
AI/ Positional Encoding
AI/ Rotary Positional Embedding (RoPE)

Flash Attention

AI/ Flash Attention
AI/ Paper/ Flash Attention
AI/ Paper/ Flash Attention/ Appendix
AI/ Paper/ Flash Attention 2
AI/ Log-Sum-Exp(LSE) Trick
AI/ GPU Hierarchy - Thread, Memory

RAG (Retrieval Augmented Generation)

AI/ Retrieval Augmented Generation(RAG)
AI/ Paper/ Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
AI/ Beam Search

Mamba

AI/ Mamba
AI/ Paper/ Mamba
AI/ Paper/ Mamba/ Appendix
AI/ Copying Task, Selective Copying Task
AI/ Induction Heads, Associative Recall
AI/ Causal Convolution
AI/ Linear Attention
AI/ Prefix Sum(inclusive scan)
AI/ Kernel Fusion, Recomputation

DeepSeek

AI/ DeepSeek-V3
AI/ DeepSeek-R1/ R1-Zero
AI/ Paper/ DeepSeek-V3
AI/ Paper/ DeepSeek-R1
AI/ Markov Decision Process(MDP)

Contrastive Learning Models

AI/ Noise Contrastive Estimation(NCE)
AI/ Ranking Loss - Pairwise, Triplet, N-Pair, InfoNCE
AI/ SimCLR
AI/ CLIP
AI/ Paper/ Learning Transferable Visual Models From Natural Language Supervision(CLIP)
AI/ Memory Bank, Memory Attention
AI/ Momentum Contrast(MoCo)
AI/ Paper/ Momentum Contrast for Unsupervised Visual Representation Learning(MoCo)

Self-Supervised Models

AI/ Bootstrap your own latent(BYOL)
AI/ Paper/ Bootstrap your own latent: A new approach to self-supervised Learning(BYOL)
AI/ DINO(DIstillation with NO label)
AI/ Paper/ Emerging Properties in Self-Supervised Vision Transformers(Dino)
AI/ Masked Auto-Encoder(MAE)
AI/ Paper/ Masked Autoencoders Are Scalable Vision Learners(MAE)
AI/ Images with Joint-Embedding Predictive Architecture(I-JEPA)
AI/ Paper/ Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture(I-JEPA)
AI/ Hiera(Hierarchical Vision Transformer)
AI/ Paper/ Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
AI/ Video Joint-Embedding Predictive Architecture(V-JEPA)
AI/ Paper/ Revisiting Feature Prediction for Learning Visual Representations from Video(V-JEPA)
AI/ Paper/ Revisiting Feature Prediction for Learning Visual Representations from Video(V-JEPA)/ Appendix
AI/ Linear Probe, Attentive Probe

Visual Task Models

AI/ Vision Transformer(ViT)
AI/ Paper/ An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale(ViT)
AI/ Feature Pyramid Networks(FPN)
AI/ Paper/ Feature Pyramid Networks for Object Detection(FPN)
AI/ DEtection TRansformat(DETR)
AI/ Paper/ End-to-End Object Detection with Transformers(DETR)
AI/ Pix2Seq
AI/ Paper/ Pix2seq: A Language Modeling Framework for Object Detection
AI/ Segment Anything(SAM)
AI/ Paper/ Segment Anything(SAM)
AI/ Paper/ Segment Anything(SAM)/ Appendix
AI/ SAM 2
AI/ Paper/ SAM 2: Segment Anything in Images and Videos
AI/ Paper/ SAM 2/ Appendix
AI/ Focal Loss
AI/ Paper/ Focal Loss for Dense Object Detection
AI/ Bipartite Matching

Multi Modality

AI/ Products of Experts(PoE), Mixture of Experts(MoE)

Stereo Vision

AI/ Camera Model
AI/ Camera Transformation, Intrinsic, Extrinsic
AI/ Weak Perspective Model, Orthographic Projection Model
AI/ Camera Calibration
AI/ Transformations
AI/ Vanishing Points and Lines
AI/ Epipolar Geometry
AI/ Camera Projection Matrix
AI/ Essential Matrix, Fundamental Matrix
AI/ Image Rectification
AI/ Triangulation
AI/ Structure From Motion(SFM), Bundle Adjustment
AI/ Active Stereo, Volumetric Stereo
AI/ Hough Transform
AI/ Feature Tracking
AI/ Optical Flow
AI/ Motion field
AI/ Quaternion Rotation
AI/ StereoBM, StereoSGBM
AI/ Paper/ Flow-Guided Online Stereo Rectification for Wide Baseline Stereo
Made with