konstantinosKokos / ape
🧮 Algebraic Positional Encodings.
☆12Updated 3 months ago
Alternatives and similar repositories for ape:
Users that are interested in ape are comparing it to the libraries listed below
- Source code for the paper "Positional Attention: Out-of-Distribution Generalization and Expressivity for Neural Algorithmic Reasoning"☆14Updated 3 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 11 months ago
- The Energy Transformer block, in JAX☆57Updated last year
- ☆32Updated 7 months ago
- Experiments on the impact of depth in transformers and SSMs.☆25Updated 6 months ago
- ☆13Updated 2 months ago
- Implementation of Spectral State Space Models☆16Updated last year
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- Minimum Description Length probing for neural network representations☆19Updated 3 months ago
- ☆21Updated 7 months ago
- Official code for paper: Conservative objective models are a special kind of contrastive divergence-based energy model☆14Updated last year
- Official repository for the paper "Exploring the Promise and Limits of Real-Time Recurrent Learning" (ICLR 2024)☆11Updated last year
- ☆11Updated 2 months ago
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- A Scalable Approximate Method for Probabilistic Neurosymbolic Inference☆15Updated 3 months ago
- Differentiable Euler Characteristic Transform☆17Updated 10 months ago
- Repository for Sparse Universal Transformers☆17Updated last year
- Quantification of Uncertainty with Adversarial Models☆28Updated last year
- ☆10Updated 2 years ago
- Your favourite classical machine learning algos on the GPU/TPU☆20Updated 4 months ago
- ☆31Updated last year
- Efficient Scaling laws and collaborative pretraining.☆16Updated 3 months ago
- The application is a end-user training and evaluation system for standard knowledge graph embedding models. It was developed to optimise …☆18Updated 2 weeks ago
- 📰 Computing the information content of trained neural networks☆21Updated 3 years ago
- ☆15Updated last year
- Efficient Computation of d-Dimensional Earth Mover's Distance☆9Updated last year
- PyTorch implementation for "Probabilistic Circuits for Variational Inference in Discrete Graphical Models", NeurIPS 2020☆17Updated 3 years ago
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]☆19Updated last month
- Evaluation of neuro-symbolic engines☆35Updated 9 months ago