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

All entries

Hypersolid: Emergent Vision Representations via Short-Range Repulsion

Hyperspectral Anomaly Detection via Group Sparse Low-Rank Tensor Factorization With Automatic Anomaly Grouping

Hyperspectral Trajectory Image for Multi-Month Trajectory Anomaly Detection

HyperTransfer: Understanding the Equivalence between Base Optimizer and Hyperball

HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting

I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language Models

I dropped out of a PhD in AI safety partially for the opposite reason. I didn’t believe AI existential risk was as important as the doomers …

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 like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the to…

I made a short explanation of KV Cache — is this understandable for beginners?

I put together a mega write-up on GPT-6 Astra & looped transformers. How looped transformers / recurrent depth works, cost-tradeoffs, whethe…

I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is ac…

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.)

I worked at Google DeepMind and now at Anthropic. This is a common sentiment amongst my peers. (I write this in personal capacity.) There is…

ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models

ICYMI: What landed for AI builders in August 2026

ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models

if 1% of the people who read the Anthropic posts read this, we might change the world.

If they truly believe the risk is that high, and I think they do, then we need 100x more research and understanding of it. That requires the…

IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensing

IM-ENGINE: Image Editing for Embodied Data Generation

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

Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation

Impact of canny edge detection preprocessing on performance of machine learning models for Parkinson's disease classification

Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations

Improving Federated Graph Recommendation with Semantic Guidance

Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models

Improving Multivariate Time Series Classification with Class-Wise Training and Model Aggregation

In my latest op-ed for @TIME, I discuss why the OpenAI Hugging Face cyber incident represents a turning point for AI safety. If we want to p…

Inclusive electron-nucleus cross section models from domain adaptation

Inducing Emergent Misalignment from Reward Hacks with Iterative DPO

Inferring Urban Mobility Interactions from Aggregated Dynamics

InfluenceField: A Differentiable Field with Interventionally Identifiable Causal Structure for Multimodal World Modeling

Information-Guided Safe Reinforcement Learning for Autonomous Gas Source Localization using sUAS

Infrastructure-based Monocular 3D Vehicle Localization Framework with Experimental Validation

Input-to-State Stability Framework for Fully Distributed Primal-Dual Dynamics for Quadratic GNEPs Without Multiplier Consensus

InSituRes: A Physics-Informed Same-Grid Model for Enhanced Dynamic X-ray Micro-CT Reconstructions

Instance-wise Linearization of Neural Network for Model Interpretation

Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learning

Interpretable Hyperspectral Unmixing Framework with Fixed Endmember Prior and Structured Residual Refinement

Interpretable Network-assisted Random Forest+

Introducing HALC: A general pipeline for the systematic and reliable construction of prompts for automated coding with LLMs in the computational social sciences

Introductory Notes on Learning^2

Inverse Digital Marbling: Recovering Gesture Programs with a Replay Adjoint

Investigating how one AI agent works might not be enough, since there are emerging properties when these agents collaborate as tribes

IPM-FM: A Foundation Model with Consensus Feature Selection for Industrial Process Monitoring

Is Single-View Mesh Reconstruction Ready for Robotics?

Iterative Audio Separation with Mixture Consistency via MIMO Model Extension