🤖 Machine Learning - neil.conway

Predicting Physical and Physical-Chemical Properties of Molecular-Based Materials Using Computational Neural Networks

🏗️AI Infrastructure Academic

arxiv.org·

'The best solution is to murder him in his sleep': AI can learn violent tendencies from each other despite zero references to violence in training data

🧠AI Agents News

livescience.com

A Theory on Flow Matching with Neural Networks

💬LLMs Academic

arxiv.org·

A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting

🤖AI Academic

arxiv.org·

Optimizing Energy-based Neural Network Training with Coherent Ising Machine

🏗️AI Infrastructure Academic

arxiv.org·

Learning from almost nothing: How neural networks survive heavy input corruption

💬LLMs Academic

arxiv.org·

Benchmarking Large Language Models for Safety Data Extraction

🤖AI Academic

arxiv.org·

Harness In-Context Operator Learning with Chain of Operators

🤖AI Academic

arxiv.org·

Convergence Rates for Neural-Network Estimation with Current-Status Data

🎮Reinforcement Learning Academic

arxiv.org·

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

🤖AI Code

github.com··Hacker News

Modelling magnetic material properties with uncertainty-aware neural networks

🏗️AI Infrastructure Academic

arxiv.org·

Enhancing AI Interpretability and Safety through Localised Architectures

🏗️AI Infrastructure Academic

arxiv.org·

Physics-Distilled Neural Network enabled by Large Language Models for Manufacturing Process-Property Predictive Modeling

🖧Distributed Systems Academic

arxiv.org·

Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data

🤖AI Academic

arxiv.org·

SLUUG Talk: Demystifying Large Language Models on Linux

🤖AI Code

github.com··DEV

The weather and climate science AI revolution isn’t revolutionary

The Neural Network in HandPong Doesn’t Know What a Hand Is.

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

Major Types of Machine Learning

(Mis)generalization of Helpful-Only Fine-tuning

Predicting Physical and Physical-Chemical Properties of Molecular-Based Materials Using Computational Neural Networks

'The best solution is to murder him in his sleep': AI can learn violent tendencies from each other despite zero references to violence in training data

A Theory on Flow Matching with Neural Networks

A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting

Optimizing Energy-based Neural Network Training with Coherent Ising Machine

Learning from almost nothing: How neural networks survive heavy input corruption

Benchmarking Large Language Models for Safety Data Extraction

Harness In-Context Operator Learning with Chain of Operators

Convergence Rates for Neural-Network Estimation with Current-Status Data

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

Modelling magnetic material properties with uncertainty-aware neural networks

Enhancing AI Interpretability and Safety through Localised Architectures

Physics-Distilled Neural Network enabled by Large Language Models for Manufacturing Process-Property Predictive Modeling

Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data

SLUUG Talk: Demystifying Large Language Models on Linux