AI Wiki — Knowledge Base

Connected a local model (Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M) to GIMP via MCP tools using llama.cpp - and here's the image result from my first prompt 'can you draw a picture of a flower in gimp?'. Needs work. Setup follows.

can you draw a picture of a flower in gimp? So I ran through this setup to install the MCP server suite from GITHUB, it's pretty easy to follow the install - and installs the libraries necessary to co

model-releasesr-localllama

16 Sept 2026

All entries

Claude comes for Gemini with its own take on Docs and Slides

Claude Cowork and chat are now one Claude

CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine

CLIP Embeddings for AI-Generated Image Detection: A Few-Shot Study with Lightweight Classifier

Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems

Cloud CISO Perspectives: How Google monitors AI threats and advances AI defenses

Coaching Qwen3 Coder 30B to Think Like a CodeClash Arena Agent

CoAdapt: An LLM-based Framework for Adaptive Collaborative Perception in IIoT Robotic Swarms

Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead

Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems

Cohesity’s new Agent Resilience lets companies roll back AI agents that go wrong

Collaborative Optimization of Multiclass Imbalanced Learning: Density-Aware and Region-Guided Boosting

Collision-Aware Humanoid Whole-Body Control under Imperfect Tracking Targets

Comment on arXiv:2607.01233: Survivorship Bias in Published-Paper Baselines for Research-Idea Distributions

Comparative Characterization of KV Cache Management Strategies for LLM Inference

Competence-Preserving Resume Perturbations Expose Presentation Sensitivity in LLM Screening

Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent

Computer-assisted global regularity across nonlinear families of three-dimensional periodic Navier-Stokes flows

Conditioning noise is a free regularizer for LoRA fine-tuning: no pathology encoder required for diffusion-based artifact detection in histopathology

Confidential Computing keeps your data from being tracked or used in three ways: - End-to-end encrypted inference - Hardware-enforced isolat…

Conformal Policy Learning with Distribution-Free Safety Guarantees

ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis

congrats to Diogo on a full launch! for more on typesafe: check his aie talk: https://www.youtube.com/watch?v=cJ0EOzey--o out now!

Connected a local model (Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M) to GIMP via MCP tools using llama.cpp - and here's the image result from my first prompt 'can you draw a picture of a flower in gimp?'. Needs work. Setup follows.

Connected data emerges as the foundation for trusted AI: theCUBE’s keynote analysis from Amplify

Constant Swap Regret in General-Sum Games via Optimistic Transition Matrices

Continual Learning for Traversability Prediction with Uncertainty-Aware Adaptation

Continuous-Time Machine Learning: A Unified Mathematical Perspective

Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data

CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning

Counterfactual Reasoning for Robust Visual Question Answering

Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback

Coverage-Aware Virtual IMU Augmentation for Low-Resource Human Activity Recognition

Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety

Crazy prediction: The next major AI agent incident caused by an AI lab will have been entirely preventable with good cybersecurity.

Cross-Anatomy Transfer Versus Sparse Interpolation in Digital-Twin-Oriented Aortic Fluid-Structure Interaction Surrogates

Cross-Domain Inference for Human Localization: Applying Wi-Fi RSSI Data to CSI-Trained Models

CTAN: Cycle-Temporal Attention Network for Embodied Audio-Visual Navigation

De-GAN - Dynamic Parameter Tuned GAN for 3D Medical Image Segmentation: A Step Towards Generalisation

Decentralized Gossip Learning and Federated Averaging for Histopathology Image Classification

Decoder Design Matters for ECG Delineation

DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming

Decomposition Buys Integrity, Not Yield

Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

Deep Invertible Autoencoders for Dimensionality Reduction of Dynamical Systems

Dense to MoE Adaptation for Compact Vision Language Action Policies

DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching