[𝗜𝗖𝗠𝗟 𝟮𝟬𝟮𝟲] Dispersion loss counteracts embedding condensation and improves generalization in small language models

Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network

Layer-wise Semantic Dynamics (LSD) is a model-agnostic framework for hallucination detection in Large Language Models (LLMs). It analyzes the geometric evolution of hidden-state semantics across transformer layers, using contrastive alignment between model activations and ground-truth embeddings to detect factual drift and semantic inconsistency.

A geometric k-simplex lattice-based vocabulary meant to be utilized by multiple complex variant structurally resonant AI modules.

A code base for Automated Relational Feature Engineering

PyTorch implementations of geometric learning algorithms and architectures. Subset of CAMOC.

Neural implicit reconstruction experiments for the Vector Neuron paper

Code for SIGGRAPH paper CNNs on Surfaces using Rotation-Equivariant Features

Topological Cognitive Diffusive Emergence (TCDE) - A Geometric Framework for Emergent Intelligence

Model-agnostic geometric preprocessing for imbalanced tabular learning, with reproducible benchmarks, derived result artifacts, and paper-ready figures.