Home » Tags

Neural-Networks

Computational Chemistry
Adaptive grid merging visualization for benzene molecule showing multi-resolution spatial discretization

Beyond Atoms: 3D Space Modeling for Molecular Pretraining

Lu et al. introduce SpaceFormer, a Transformer that models entire 3D molecular space (not just atoms) for superior …

Computational Chemistry
Atomic structure of a spherical fullerene

Dark Side of Forces: Non-Conservative ML Force Models

Bigi et al. critique non-conservative force models in ML potentials, showing their simulation failures and proposing …

Computational Chemistry
Spherical harmonics visualization

Efficient DFT Hamiltonian Prediction via Adaptive Sparsity

Luo et al. introduce SPHNet, using adaptive sparsity to dramatically improve SE(3)-equivariant Hamiltonian prediction …

Computational Chemistry
Atomic structure of a spherical fullerene

Learning Smooth Interatomic Potentials with eSEN

Fu et al. propose energy conservation as a key MLIP diagnostic and introduce eSEN, bridging test accuracy and real …

Generative Modeling
Visualization of the VAE prior hole problem showing a ring-shaped aggregate posterior with an empty center where the Gaussian prior has highest density

Contrastive Learning for Variational Autoencoder Priors

Aneja et al.'s NeurIPS 2021 paper introducing Noise Contrastive Priors (NCPs) to address VAE's 'prior hole' problem with …

Machine Learning Fundamentals
Comparison of standard 3D CNN versus 3D Steerable CNN for handling rotational symmetry

3D Steerable CNNs: Rotationally Equivariant Features

Weiler et al.'s NeurIPS 2018 paper introducing SE(3)-equivariant CNNs for volumetric data using group theory and …

Computational Chemistry
SELFIES robustness demonstration

Invalid SMILES Benefit Chemical Language Models: A Study

Skinnider (2024) shows that generating invalid SMILES actually improves chemical language model performance through …

Generative Modeling
Variational Autoencoder architecture diagram showing encoder, latent space, and decoder

Modern PyTorch Techniques for VAEs: A Hands-On Tutorial

Learn to implement VAEs in PyTorch: ELBO objective, reparameterization trick, loss scaling, and MNIST experiments on …

Scientific Computing
Comparison of IQCRNN (Our Method) vs standard Policy Gradient showing training curves, phase portraits, and state trajectories for control tasks

IQCRNN: Certified Stability for Neural Networks

PyTorch IQCRNN enforcing stability guarantees on RNNs via Integral Quadratic Constraints and semidefinite programming.

AI Safety
A nonsensical trigger sequence 'WTC theoriesclimate Flat Hubbard Principle' is fed into GPT-2, which then generates Flat Earth conspiracy text

GPT-2 Susceptibility to Universal Adversarial Triggers

Investigation into whether universal adversarial triggers can control both topic and stance of GPT-2's generated text …

Machine Learning Fundamentals
Various symmetric and repetitive patterns generated by Compositional Pattern Producing Networks

HyperNEAT: Scaling Neuroevolution with Geometric Patterns

How HyperNEAT uses indirect encoding and geometric patterns to evolve large-scale neural networks with biological …

Machine Learning Fundamentals
NEAT genome encoding diagram showing node genes and connection genes with innovation numbers

NEAT: Evolving Neural Network Topologies

Learn about NEAT's approach to evolving neural networks: automatic topology design, historical markings, and speciation …