AI Wiki — Knowledge Base

I trained an audio model that can generate infinite one-shots for music production and turn text prompts into fully playable synths. I'm not only releasing the model but I've also released a video on exactly how I did it (and the inferencing pipeline to let others make text based synths.)

(hopefully this is okay to here - it seems like audio models and image / video modeals is allowed but yeah this is a bit different) So I've been doing independent audio research for a while now. The u

model-releasesr-localllama

9 Sept 2026

model releases

Hierarchical Prompt Injector for Domain Generalization Segmentation

How Does Parameter Pruning Reshape DNN Representations? An Interaction-Driven Exploration

How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid Collaboration

How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?

Human-Centric Image Captioning with Subject-Centered Spatial Understanding

Hyperparameter Scaling Laws Across MoE Sparsity

HyperTransfer: Understanding the Equivalence between Base Optimizer and Hyperball

i just tried Muse*, connected it to my GitHub, and continued the work I was doing in ChatGPT/Claude w no interruptions which is great cuz i …

I trained an audio model that can generate infinite one-shots for music production and turn text prompts into fully playable synths. I'm not only releasing the model but I've also released a video on exactly how I did it (and the inferencing pipeline to let others make text based synths.)

ICYMI: What landed for AI builders in August 2026

Image-Scale Robustness and Visual Recognition Performance: A Cross-Architecture Analysis

Improving Federated Graph Recommendation with Semantic Guidance

Inducing Emergent Misalignment from Reward Hacks with Iterative DPO

IXPLORE: Bounded Ideal Point Estimation with Grid-Based Uncertainty Quantification

JEDI: JEPA-to-Edge Distillation for Efficient Cropland Segmentation from Satellite Imagery

L2G-Map: Local-to-Global Mapping via Hierarchical Diffusion Refinement and Elliptical Bayesian Fusion

LANTERN: A Closed-Loop Benchmark for VLM-Based Cooperative Driving with Temporally Grounded Warnings

Large Classification-Risk-Optional Label Acquisition

Last week we brought LlamaParse to Claude. Now it’s available in ChatGPT, too 🦙 ChatGPT can already read PDFs. But document work gets harde…

Latent class analysis by regularized spectral clustering

LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text

Learning Acrobatic Flight from Preferences

Learning functional components of PDEs from data using neural networks

Learning Length-Extrapolatable Recurrent Models

Livestream Alert: Comfy Agent Beta: VFX, Marketing & E-Commerce Workflows at 10am PT Comfy Agent is entering beta, and we're opening the doo…

LLM-Aided Design for Manufacturing: A Multi-Agent System for Intent-Preserving Redesign of CAD for Improved Manufacturability

Local gradient neural operator

Low-Rank Plus Sparse Matrix Transfer Learning under Growing Representations and Ambient Dimensions

LWiAI Podcast #256 - Fable 5.1, Astra Tease, Gemini 3.8 Flash

MARR: Decoupling Policy, Execution, and Calibration for All-in-One Medical Image Restoration

Masking Radar Cognition under Adversarial Surveillance: A Distributional Privacy Framework

Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy

MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation

Mention if a 'new model' is a finetune

MI-PEFT: Mixture-of-Experts Integrated Parameter-Efficient Fine-Tuning Protein Language Models Improves Acidophilic Proteins Classification

Miles v0.1: Production-Level Post-Training

MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials

MOAE: Multi-Objective Agent Evolution with Pareto-Preserving Search

MOLE: Detecting Insider Threats in AI Agents

Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation

Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias

MorphoOrgaAgent: A Foundation-Model-Based Multi-Agent System for Autonomous Organoid Analysis

MpSub: A Momentum p-Dimensional Subspace Trust-Region Method for Derivative-Free Fine-Tuning of Large Language Models

MSCA-UNet: Multi-Scale Context and Attention U-Net for Image Segmentation

Multi-Fidelity Physics-Informed Neural Networks with Bayesian Uncertainty Quantification and Adaptive Residual Learning for Efficient Solution of Parametric Partial Differential Equations

Multi-granularity Adaptive Hypergraph Representation Learning via Granular-ball

Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation

NEO-BENCH: A New Multi-Source Benchmark for Generalizable Astronomical Streak Detection