997 technical terms and definitions
diffusion model generative, denoising diffusion, ddpm ddim, latent diffusion models, stable diffusion models, text to image diffusion
Diffusion models are the generative method behind most modern image, video, and audio synthesis — Stable Diffusion, DALL-E, Midjourney, Sora and their kin. The core idea is almost…
diffusion models, models denoising, cifar dall ddpm passed, diffusion models denoising & ddpm, diffusion models denoising, models denoising ddpm, denoising ddpm
Diffusion Models: Denoising & DDPM Introduction & Motivation Diffusion models: iterative denoising process. DDPM: Denoising Diffusion Probabilistic Models. Forward: add noise…
diffusion models denoising score matching generative modeling, diffusion models, denoising score matching, 10k 123k 30k 32gb 3d 3m, diffusion models denoising
Diffusion Models: Denoising, Score Matching, and Generative Modeling 1. Introduction & Motivation Diffusion models have emerged as a powerful class of generative models that…
Diffusion Models for 3D Shape Generation Introduction & Motivation Diffusion Models for 3D Shape Generation addresses a central problem in generative modeling of diffusion data…
Diffusion Models for 3D Shape Generation (Extended Study) Introduction & Motivation Diffusion Models for 3D Shape Generation (Extended Study) addresses a central problem…
Diffusion Models for 3D Shape Generation (Extended Study) Introduction & Motivation Diffusion Models for 3D Shape Generation (Extended Study) addresses a central problem…
Diffusion Models for Audio Generation Introduction & Motivation Diffusion Models for Audio Generation addresses a central problem in generative modeling of diffusion data: how…
Diffusion Models for Audio Generation (Extended Study) Introduction & Motivation Diffusion Models for Audio Generation (Extended Study) addresses a central problem in generative…
Diffusion Models for Audio Generation (Extended Study) Introduction & Motivation Diffusion Models for Audio Generation (Extended Study) addresses a central problem in generative…
graph neural networks
Diffusion Models for Graphs (GDSS/DiGress) apply denoising diffusion probabilistic modeling to discrete graph structures — gradually corrupting a graph into noise (random edge…
Diffusion Models for Molecule Generation Introduction & Motivation Diffusion Models for Molecule Generation addresses a central problem in generative modeling of diffusion data…
Diffusion Models for Molecule Generation (Extended Study) Introduction & Motivation Diffusion Models for Molecule Generation (Extended Study) addresses a central problem…
Diffusion Models for Molecule Generation (Extended Study) Introduction & Motivation Diffusion Models for Molecule Generation (Extended Study) addresses a central problem…
Diffusion Models for Video Generation Introduction & Motivation Diffusion Models for Video Generation addresses a central problem in generative modeling of diffusion data: how…
Diffusion Models for Video Generation (Extended Study) Introduction & Motivation Diffusion Models for Video Generation (Extended Study) addresses a central problem in generative…
Diffusion Models for Video Generation (Extended Study) Introduction & Motivation Diffusion Models for Video Generation (Extended Study) addresses a central problem in generative…
denoising process, ddpm score matching
Diffusion models generate images by learning to reverse a gradual noising process. Forward process: Gradually add Gaussian noise to image over T steps until it becomes pure noise.…
sora video generation, stable video diffusion, video synthesis deep learning, temporal diffusion models
Diffusion Models for Video Generation are generative architectures that extend image diffusion frameworks to the temporal dimension, learning to denoise sequences of video frames…
graph neural networks
Diffusion on Graphs describes the process by which a signal (heat, probability, information, influence) spreads from a node to its neighbors over time according to the graph…
thermal diffusion, dopant diffusion
Diffusion — the thermal process by which dopant atoms migrate into a semiconductor lattice driven by concentration gradients, historically the primary doping method before ion…
simulation
Diffusion Simulation is the TCAD computational modeling of dopant atom migration through the silicon crystal lattice during thermal processing — predicting the spatial…
dit, scalable diffusion, dit architecture, latent diffusion transformer
Diffusion Transformer (DiT) is the architecture that replaces the traditional U-Net backbone in diffusion models with a pure Transformer design — using self-attention over patched…
dit architecture, class conditional dit, latent diffusion dit, scalable diffusion model
Diffusion Transformers (DiT) are the generative image architecture that replaces the traditional U-Net backbone in latent diffusion models with a standard Vision Transformer…
multimodal ai
Diffusion Upscaler is a super-resolution approach that uses diffusion denoising to generate high-resolution details - It can produce photorealistic high-frequency content…
digital signatures rsa pss, digital signatures rsa, signatures rsa pss, digital signatures, signatures rsa, rsa pss
Digital Signatures RSA PSS Introduction & Motivation Digital Signatures RSA PSS addresses a central problem in cryptography process control and signature-length-key-dependent…
digital thread and model based systems engineering for manufacturing, digital thread model systems engineering manufacturing, digital thread, model systems engineering
Digital Thread and Model-Based Systems Engineering for Manufacturing Introduction & Motivation Digital Thread and Model-Based Systems Engineering for Manufacturing addresses…
dac linearity and distortion characterization, dac linearity distortion, linearity distortion characterization, dac linearity, linearity distortion, distortion characterization
DAC Linearity and Distortion Characterization Introduction & Motivation DAC Linearity and Distortion Characterization addresses a central problem in analog process control…
digital twin fab model accuracy prediction, digital twin fab, twin fab model, fab model accuracy, model accuracy prediction, digital twin, twin fab, fab model, model accuracy
Digital Twin Fab Model Accuracy Prediction with Machine Learning Introduction & Motivation Digital Twin Fab Model Accuracy Prediction with Machine Learning addresses a central…
digital twin fab simulation accuracy prediction, digital twin fab, twin fab simulation, fab simulation accuracy, simulation accuracy prediction, digital twin, twin fab
Digital Twin Fab Simulation Accuracy Prediction with Machine Learning Introduction & Motivation Digital Twin Fab Simulation Accuracy Prediction with Machine Learning addresses…
digital twin modeling industrial systems, digital twin, modeling industrial systems, digital twin modeling, twin modeling industrial, twin modeling, modeling industrial, industrial systems
Digital Twin Modeling for Industrial Systems Introduction & Motivation Digital Twin Modeling for Industrial Systems addresses a central problem in asset and process lifecycle…
digital twin process simulation accuracy prediction, digital twin process, twin process simulation, process simulation accuracy, simulation accuracy prediction
Digital Twin Process Simulation Accuracy Prediction with Machine Learning Introduction & Motivation Digital Twin Process Simulation Accuracy Prediction with Machine Learning…
dijkstra algorithm shortest path prediction, dijkstra algorithm shortest, algorithm shortest path, shortest path prediction, dijkstra algorithm, algorithm shortest, shortest path
Dijkstra Algorithm Shortest Path Prediction with Machine Learning Introduction & Motivation Dijkstra Algorithm Shortest Path Prediction with Machine Learning addresses a central…
dijkstra shortest path, dijkstra shortest, shortest path
Dijkstra Shortest Path Introduction & Motivation Dijkstra Shortest Path addresses a central problem in algorithms process control and path-optimality-guarantee prediction: how…
llm architecture
Dilated Attention is a sparse attention pattern where each token attends to positions at regular intervals (dilation rate d) rather than consecutive positions — similar to dilated…
dilution refrigerator cooldown stability prediction, dilution refrigerator cooldown, refrigerator cooldown stability, cooldown stability prediction, dilution refrigerator
Dilution Refrigerator Cooldown Stability Prediction with Machine Learning Introduction & Motivation Dilution Refrigerator Cooldown Stability Prediction with Machine Learning…
chemistry ai
DimeNet (Directional Message Passing Neural Network) is an equivariant molecular GNN that incorporates bond angles into message passing by encoding the angular geometry between…
graph neural networks
DimeNet is directional message-passing graph network that explicitly models bond angles. - It improves molecular property prediction by encoding geometric interactions beyond…
Dimensionality Reduction for Visualization Introduction & Motivation Dimensionality Reduction for Visualization addresses a central problem in explainability interpretation…
dimensionality reduction time series, dimensionality reduction time, reduction time series, dimensionality reduction, reduction time, time series
Dimensionality Reduction Time Series Introduction & Motivation Dimensionality Reduction Time Series addresses a central problem in timeseries process control…
dinic algorithm blocking flow, dinic algorithm blocking, algorithm blocking flow, dinic algorithm, algorithm blocking, blocking flow
Dinic Algorithm Blocking Flow Introduction & Motivation Dinic Algorithm Blocking Flow addresses a central problem in algorithms process control and time-complexity-polynomial…
dino, computer vision
DINO pre-training is the self-distillation framework where a student network learns to match teacher outputs across augmented views without negative pairs or labels - it drives…
DINO Self-Attention Vision Introduction & Motivation DINO Self-Attention Vision addresses a central problem in vision processing and attention-interpretability-quality prediction…
DINO Self-Distillation Method Introduction & Motivation DINO Self-Distillation Method addresses a central problem in selfsupervised and teacher-student-momentum architecture: how…
DINO Emerging Properties in Self-Supervised Vision Transformers Introduction & Motivation DINO Emerging Properties in Self-Supervised Vision Transformers addresses a central…
DINOv2 Learning Robust Visual Features Without Supervision Introduction & Motivation DINOv2 Learning Robust Visual Features Without Supervision addresses a central problem…
diode reverse recovery time prediction, diode reverse recovery, reverse recovery time, recovery time prediction, diode reverse, reverse recovery, recovery time, time prediction
Diode Reverse Recovery Time Prediction with Machine Learning Introduction & Motivation Diode Reverse Recovery Time Prediction with Machine Learning addresses a central problem…
diode reverse recovery time prediction, diode reverse recovery, reverse recovery time, recovery time prediction, diode reverse, reverse recovery, recovery time, time prediction
Diode Reverse Recovery Time Prediction with Machine Learning Introduction & Motivation Diode Reverse Recovery Time Prediction with Machine Learning addresses a central problem…
diode switching transient ringing prediction, diode switching transient, switching transient ringing, transient ringing prediction, diode switching, switching transient
Diode Switching Transient Ringing Prediction with Machine Learning Introduction & Motivation Diode Switching Transient Ringing Prediction with Machine Learning addresses a central…
dip package lead forming drift prediction, dip package lead, package lead forming, lead forming drift, forming drift prediction, dip package, package lead, lead forming
DIP Package Lead Forming Drift Prediction with Machine Learning Introduction & Motivation DIP Package Lead Forming Drift Prediction with Machine Learning addresses a central…
generative models
DIP-VAE (Disentangled Inferred Prior VAE) is a VAE variant that encourages disentangled representations by directly regularizing the aggregate posterior q(z) = E_{p(x)}[q(z x)]…