minhtannguyen / transformer-mgk
This is the public github for our paper "Transformer with a Mixture of Gaussian Keys"
☆26Updated 2 years ago
Alternatives and similar repositories for transformer-mgk:
Users that are interested in transformer-mgk are comparing it to the libraries listed below
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆60Updated 3 years ago
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆16Updated last year
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19Updated 2 weeks ago
- [ICLR 2023] “ Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Better Representations”, Ziyu Jian…☆24Updated 2 years ago
- DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization☆29Updated 2 years ago
- Implementation of TableFormer, Robust Transformer Modeling for Table-Text Encoding, in Pytorch☆37Updated 3 years ago
- Github code for the paper Maximum Class Separation as Inductive Bias in One Matrix. Arxiv link: https://arxiv.org/abs/2206.08704☆29Updated 2 years ago
- Code for the PAPA paper☆27Updated 2 years ago
- PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)☆71Updated last year
- Diffusion based transformer, in PyTorch (Experimental).☆24Updated 2 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- Deep Learning & Information Bottleneck☆60Updated last year
- A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in y…☆45Updated 2 years ago
- Code for "Don't trust your eyes: on the (un)reliability of feature visualizations" (ICML 2024)☆32Updated last year
- ☆57Updated 2 years ago
- Official PyTorch implementation for NeurIPS'24 paper "Knowledge Composition using Task Vectors with Learned Anisotropic Scaling"☆19Updated 2 months ago
- ☆21Updated 2 years ago
- ☆26Updated 3 years ago
- [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)☆34Updated last year
- Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"☆15Updated 2 years ago
- ☆18Updated 3 years ago
- Position Prediction as an Effective Pretraining Strategy☆8Updated 2 years ago
- Decoupled Kullback-Leibler Divergence Loss (DKL), NeurIPS 2024 / Generalized Kullback-Leibler Divergence Loss (GKL)☆44Updated 3 weeks ago
- Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning☆44Updated last year
- Implementation for ACProp ( Momentum centering and asynchronous update for adaptive gradient methdos, NeurIPS 2021)☆15Updated 3 years ago
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 3 years ago
- ☆36Updated 4 years ago
- PyTorch implementation of FNet: Mixing Tokens with Fourier transforms☆27Updated 3 years ago
- Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…☆50Updated 2 years ago
- ☆81Updated 8 months ago