watcl-lab / positional_attentionLinks
Source code for the paper "Positional Attention: Expressivity and Learnability of Algorithmic Computation"
☆14Updated 4 months ago
Alternatives and similar repositories for positional_attention
Users that are interested in positional_attention are comparing it to the libraries listed below
Sorting:
- ☆58Updated last year
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated 2 years ago
- ☆34Updated last year
- An annotated implementation of the Hyena Hierarchy paper☆34Updated 2 years ago
- Scalable and Stable Parallelization of Nonlinear RNNS☆22Updated last month
- Deep Networks Grok All the Time and Here is Why☆37Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated last year
- Your favourite classical machine learning algos on the GPU/TPU☆20Updated 9 months ago
- ☆82Updated last year
- ☆85Updated last year
- A State-Space Model with Rational Transfer Function Representation.☆81Updated last year
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆51Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆41Updated last year
- Simple Scalable Discrete Diffusion for text in PyTorch☆36Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆89Updated last year
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 8 months ago
- ☆33Updated 11 months ago
- JAX/Flax implementation of the Hyena Hierarchy☆34Updated 2 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆91Updated last year
- Code for the paper "Function-Space Learning Rates"☆23Updated 4 months ago
- ☆33Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆67Updated last year
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]☆20Updated this week
- H-Net Dynamic Hierarchical Architecture☆80Updated 3 weeks ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- The Energy Transformer block, in JAX☆59Updated last year
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- ☆30Updated 2 months ago