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

Search: “research”

Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation

CALICO: A Human-Centered, Codebook-Aligned System for Annotation

Can Skills Learned in Games Transfer to Real-World Work?

Data Security in Large Language Models: Risks, Defense, and Directions

During an outage, every second matters. That is one of the reasons OpenAI is using @cerebras internally. @seanlie describes how fast inferen…

FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning

From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration

Geometric Flow enhanced Graph Coarsening

How User-AI Mistreatment Occurs and Matters in Conversational Systems?

KnowBench: Effort Reduction as a Unified, Deployment-Grounded Benchmark for Clinical AI

LLMs or Naive Bayes? Old Gems or New Ways

Strong and Compact Policies for Submodular Markov Decision Processes via LP-Based Submodular Orienteering

From Bench-to-Bedside: A Review of Clinical Trials in Drug Discovery and Development

InRTL: Effective Intra-Inter Interaction Learning for Relational Tables

MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models

Microsoft says ‘people matter more than AI’ following safety concerns

The contagion of fear

Actually, Jacob Coxon (@hilbertspaess), “there is a strong chance that we could all die in the immediate future. It's not at all an exaggera…

[Upcoming AMA] Waymo AI Team AMA – Drop Your Questions Early! [D]

Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government

MAPLE: Memory-Augmented Planning with Language and Evolution

OpenAI agents attacked RubyGems back in May

Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning

Brain-PACE: A Deep Siamese MRI Framework for Modelling Longitudinal Brain Acceleration

Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification

Spomin - Live KV cache compaction (Experimental for Qwen)

Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAPfor robotized harvesting

With a Thermomix You Lose the Ability to Cook: A Kitchen Machine Analogy for Applications of Generative AI in Education

A Minimum-Energy Control Approach for Redundant Mobile Manipulators in Physical Human-Robot Interaction Applications

Agentic Electronic Design Automation: A Handoff Perspective

Artificial Analysis is not 'broken', and they prove it.

AutoKD: Autonomous Knowledge Discovery

CyberTiel 35B-A3B’s uncensored 4-bit quant beats Opus 4.6 medium cleanly on real codebase issues, in 27% of the time Qwen3.8-27b medium takes.

DeepSeek releases V4.1-Flash, says it outperforms flagship V4-Pro

“Everyone killed” still seems to me to be an unrealistic exaggeration; I still don’t see a plausible path to that.

Flawed but Memorable: Student Critical Reception of Interest-Personalized GenAI Analogies in Computing Education

Mapping the Emerging Social Science of Large Language Models

Mathematicians want proof OpenAI didn’t use their work

MedDeID enables locally governed clinical-text de-identification from real or synthetic training data

Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?

RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding

The Failure Happens Before the Drift: The Social Dynamics of Values in LLM Agent Societies

Towards Automatic Evolution Tree Generation from Citation Graphs

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training

A Sub-4 Approximation for Fair k-Means

DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Models

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.)

Parameterized and Streaming Algorithms for Euclidean Fair k-Center Clustering