Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network
-
Updated
Jul 26, 2024 - Python
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.
Code for SIGGRAPH paper CNNs on Surfaces using Rotation-Equivariant Features
Neural implicit reconstruction experiments for the Vector Neuron paper
Topological Cognitive Diffusive Emergence (TCDE) - A Geometric Framework for Emergent Intelligence
Add a description, image, and links to the geometric-learning topic page so that developers can more easily learn about it.
To associate your repository with the geometric-learning topic, visit your repo's landing page and select "manage topics."