diffusion models

ASTDGCN: An Adaptive Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Forecasting

An adaptive spatial–temporal diffusion graph convolutional network (ASTD-GCN) is advanced for a traffic flow prediction model that integrates adaptive graph learning, diffusion convolution, and bi-directional long short-term memory network (Bi-LSTM) with attention mechanism, showing better predictive precision in traff...

Artificial Intelligence in Healthcare and Drug Discovery: From Predictive Diagnostics to Precision Medicine

The integration of artificial intelligence (AI) and deep learning with the biomedical research marks a critical inflection point, shifting the paradigm from addressing symptoms to predicting and acting at the molecular level. In many diagnostic models, the chain reaction triggered by a chronic infection is often overlo...

Verified Deep Learning with Lean 4

A formal verification of the math of modern deep learning, written as a Lean 4 blueprint project and shipped as the code it proves. Mathlib's fderiv is the foundation; every layer's backward is derived as a vector-Jacobian product rather than asserted -- dense, ReLU, softmax cross-entropy, 2D convolution, max-pool, Bat...

Verified Deep Learning with Lean 4

A formal verification of the math of modern deep learning, written as a Lean 4 blueprint project and shipped as the code it proves. Mathlib's fderiv is the foundation; every layer's backward is derived as a vector-Jacobian product rather than asserted -- dense, ReLU, softmax cross-entropy, 2D convolution, max-pool, Bat...

KODEX — KGEN: generative

KODEX — KGEN (generative). generative surrogate — a PCA/latent model that samples plausible equilibrium flux fields; diffusion is the roadmap upgrade Benchmark: generative (PCA latent, dim 8); samples plausible equilibrium fields (diffusion = roadmap) Part of KODEX, the Kronos Family of Codes — a benchmarked AI/ML fusi...

A Critical Vocabulary for Artificial Intelligence: Terms for the politics and ideology of large language and diffusion models

The AI industry supplies most of the words we use to describe its technology. It has been delivered to us through analogies of thinking machines, intelligence, and parallels to human cognition. Alternate vocabulary is a useful tool for creating clarity beyond the industry’s frame. This page collects and clarifies termi...

Anomalous transport in the planetary boundary layer: A three-dimensional time-fractional advection–diffusion model

Zero-shot rib design: Merging a training-free generative prior with topology optimization

This work treats a frozen text-to-image diffusion model as a training-free source of design knowledge and distills it into the physics loop of density-based topology optimization via score distillation sampling, so that a text prompt becomes an explicit, machine-interpretable representation of engineer intent.

Traveling wave solutions of a hybrid local-nonlocal dispersal SIR model with diffusion and incidence delays

From unstable conditioning to disentangled prompts: Variance-stable diffusion model for harsh underwater image enhancement

User preference generation and recommendation of new energy vehicles based on diffusion model and multimodal knowledge graph

Spatio-temporal dynamics of vegetation-water model with root hydrotropism and cross diffusion