AI Wiki — Knowledge Base

InvokeAI 6.13 just released, its largest community-driven release ever. Adds full support for Anima & Qwen Image, support for API models (like GPT Image), support for Prompt Expansion & Image To Prompt, lasso & polygon tools, overhauled docs website and more

InvokeAI 6.13 is the largest community-driven release of the software, adding full support for Anima & Qwen Image models, API model integration (such as GPT Image), and new features including Prompt E

model-releasesr-stablediffusion

27 May 2026

Search: “models”

Representation Forcing for Bottleneck-Free Unified Multimodal Models

Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation

Aggregate Models, Not Explanations: Improving Feature Importance Estimation

Contrastive Representation Regularization for Vision-Language-Action Models

libhmm: A Modern C++20 Library for Hidden Markov Models with Correct MLE Emission M-Steps

MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models

Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering

open models are having a moment!

open models will become a huge force for coding.

Procedural Pretraining: Warming Up Language Models with Abstract Data

ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving

When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis

Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach

Assessing Factual Music Comprehension in Large Audio Language Models

Benchmarking Ultrasound Foundation Models for Fetal Plane Classification

BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models

Can Decision Trees Teach Large Language Models? Distilling Verbalized Knowledge for Molecular Property Prediction

Compositional Generalization in Autoregressive Models via Logit Composition

Do Clinical Models Change Treatment Decisions?

Local MDI+: Local Feature Importances for Tree-Based Models

📢Qwen3.7-Max just hit #3 on ITbench-AA — a fresh benchmark testing how well models handle real-world enterprise IT tasks, agentic-style. 🔧…

Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales

Advancing Creative Physical Intelligence in Large Multimodal Models

Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice

Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting

CleanSurvival: Automated data preprocessing for time-to-event models using reinforcement learning

Guiding Token-Sparse Diffusion Models

InvokeAI 6.13 just released, its largest community-driven release ever. Adds full support for Anima & Qwen Image, support for API models (like GPT Image), support for Prompt Expansion & Image To Prompt, lasso & polygon tools, overhauled docs website and more

PersianMedQA: Evaluating Large Language Models on a Persian-English Bilingual Medical Question Answering Benchmark

PitchBench: Measuring Pitch Hearing in Audio-Language Models

Characterizing Linear Alignment Across Language Models

Cross-Domain Generalization Limits of Vision Foundation Models in Facial Deepfake Detection

Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement

Gemma 4 adoption numbers outpacing Qwen 3.5/3.6 for the same sized models is a big shift in the international balance of influence via open …

Nano World Models: A Minimalist Implementation of Future Video Prediction

Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models

Topology-Driven Transferability Estimation of Medical Foundation Models for Segmentation

TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models

UWM-JEPA: Predictive World Models That Imagine in Belief Space

BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models

Evaluating Customized vs. Generalist Transformer-based Models for Legal Contract Classification

The physics of AI weather models

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models

HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection

Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators

Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models

Beyond Acoustic Emotion Recognition: Multimodal Pathos Analysis in Political Speech Using LLM-Based and Acoustic Emotion Models