AI Wiki — Knowledge Base

GitHub - orion4d/Orion4D_anaglyph: Orion4D Anaglyph** is a high-performance custom node designed to transform 2D images into stereoscopic (3D) renders via a depth map. It offers total control over parallax, convergence, and depth processing to ensure optimal visual comfort

Orion4D Anaglyph is a custom node that converts 2D images into stereoscopic 3D renders using depth maps, offering adjustable parameters for parallax, convergence, and depth processing. Designed for hi

local-air-stablediffusion

2 Jun 2026

All entries

GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation

@garrytan Model, application, and infrastructure layers trying to commoditize each other

Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs

GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning

GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics

GeistBERT: Breathing Life into German NLP

Gemini Spark is the most impressive and terrifying AI experience I’ve had yet

General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling

Generalization Limits in Vehicle Re-Identification

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime

Generalized Guarantees for Variational Inference in the Presence of Even and Elliptical Symmetry

Generate a complete storyboard from a single prompt, then animate it in Seedance 2.0 using a reference image. This ComfyUI workflow uses LLM…

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation

Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey

Generative AI and Sales Productivity: Field Experiments in Online Retail

Generative Diffusion Priors for 3D Mapping of the Dark Universe

Generative Multi-Robot Motion Planning via Diffusion Modeling with Multi-Agent Reinforcement Learning Guidance

Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models

GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing

Geodesic Flow Matching for Denoising High-Dimensional Structured Representations

Geodesics with Unified Tangent-constrained Priors and Curvature Regularization

Geometric Erasure by Contrastive Velocity Matching in Rectified Flows

Geometric Latent Reasoning Induces Shorter Generations in LLMs

Geometry-Aware Implicit Memory for Video World Models

Geometry-Aware Probabilistic Circuits via Voronoi Tessellations

GeoSAM-3D: Geodesic Prompt Propagation for Open-Vocabulary 3D Scene Segmentation from Monocular Video

getting hair and makeup with the tech style icon @saranormous

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools

GIFT: Geometry-Induced Functional Transfer for Category-level Object Manipulation

GIRL-DETR: Gradient-Isolated Reinforcement Learning for Video Moment Retrieval

GitHub - orion4d/Orion4D_anaglyph: Orion4D Anaglyph** is a high-performance custom node designed to transform 2D images into stereoscopic (3D) renders via a depth map. It offers total control over parallax, convergence, and depth processing to ensure optimal visual comfort

GitHub - orion4d/Orion4D_maskpro: Mask editor for ComfyUI

GitHub - orion4d/Orion4D_TextMakerPro: TextMakerPro is a ComfyUI custom node and browser-based text/layout editor designed to create stylized text images directly from ComfyU

GitHub unveils a GitHub Copilot desktop app in technical preview, which introduces a new feature called canvases for bidirectional work between users and agents (Mario Rodriguez/The GitHub Blog)

GitHub's plan for Agents — Kyle Daigle, GitHub

Giving agents access to sensitive systems shouldn’t mean handing them your secrets. With Fleet access profiles, agents running in sandboxes …

GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks

GLENS: Global Search via Learning from Solver Iterates with Diffusion Models

GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes

Global Convergence of a Line-Search Filter Differential Dynamic Programming Method

Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation

Global Geometry Is Not Enough for Vision Representations

Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotion

Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures

GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction

GNMR: Runtime Stability Control for Low-Precision Large Language Model Training

GNN-Enabled Robust Hybrid Beamforming with Score-Based CSI Generation and Denoising