A Brief Introduction to Prompt Tuning Permalink
This article aims to provide a brief overview of Prompt Tuning Method for Language Model Adaptation from the Google Research Lab along with code and interact...
Posts by Category
Paper Summaries
Brief Introduction to P-Tuning Permalink
This articles aims to provide a brief overview of the paper “GPT Understands, Too”, joint work from Tsinghua University and MIT that introduced P-Tuning as a...
Introduction to Chebyshev Graph Convolutional Neural Networks Permalink
This article provides a brief overview of Chebyshev Graph Convolutional Neural Networks (ChebGCN) which solves the orthogonality problem of LapGCNs, complete...
VICReg - Variance-Invariance-Covariance Regularization for Self Supervised Learning Permalink
Intuitive and step-by-step guide to understanding the VICReg framework for Self Supervised Learning, along with interactive visualizations and code
Multi-Task Self Supervised Graph Representation Learning Permalink
Brief breakdown of Multi-task Self-supervised Graph Neural Network Enable Stronger Task Generalization [ICLR 2023] by Mingxuan Ju, Tong Zhao, Qianlong Wen, W...
A Brief Introduction to Graph Contrastive Learning Permalink
This article provides an overview of “Deep Graph Contrastive Representation Learning” and introduces a general formulation for Contrastive Representation Lea...
Multi-view Graph Representation Learning Permalink
Easy to digest breakdown of “Contrastive Multi-View Representation Learning on Graphs” by Kaveh Hassani and Amir Hosein Khasahmadi
Graph Contrastive Learning Permalink
An overview of “Deep Graph Contrastive Representation Learning”
What is (AdaLoRA) Adaptive Budget Allocation for LoRA Permalink
An overview of Adaptive Budget Allocation for Parameter Efficient Fine-Tuning
What is QLoRA? Permalink
An overview of (QLoRA) Efficient Finetuning of Quantized LLMs
What Are Intrinsic Dimensions? The Secret Behind LoRA Permalink
An overview of Intrinsic Dimensions and how they enable Low-Rank Domain Adaptation (LoRA)
A Brief Introduction to (LoRA) Low-Rank Adaptation of Large Language Models Permalink
An overview of “Low-Rank Adaptation of Large Language Models”
A Brief Introduction to Mixture Model Networks (MoNet) Permalink
brief overview of the Mixture Model Networks (MoNet) architecture
A Brief Introduction to Graph Attention Networks Permalink
brief overview of the Graph Attention Networks architecture
A Brief Introduction to Residual Gated Graph Convolutional Networks Permalink
brief overview of the Residual Gated Graph Convolutional Network architecture
An Introduction to GraphSAGE Permalink
A brief overview of GraphSAGE
What are Graph Isomorphism Networks? Permalink
A brief overview of Graph Isomorphism Networks (GIN)
An Introduction to Convolutional Graph Neural Networks Permalink
A beginner friendly introduction to Convolutional Graph Neural Networks (GCNs).
An Introduction to Graph Attention Networks Permalink
A beginner friendly introduction to Attention based Graphical Neural Networks (GATs).
An Introduction to Message Passing Graph Neural Networks (GNNs) Permalink
A beginner friendly introduction to Message Passing Graph Neural Networks (MPGNNs).
Graph Neural Networks (GNNs) with Learnable Structural and Positional Representations Permalink
An in-depth breakdown of “Graph Neural Networks with Learnable Structural and Positional Representations” by Vijay Prakash Dwivedi, Anh Tuan Luu, Thomas Laur...
MLP-Mixer: An all-MLP Architecture for Vision Permalink
In the past few months there have been various papers proposing MLP based architectures without Attention or Convolutions. This report analyses the paper ‘ML...
DINO - Emerging Properties in Self-Supervised Vision Transformers Permalink
Breakdown of Emerging Properties in Self-Supervised Vision Transformers by Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojan...
What Do Compressed Deep Neural Networks Forget? Permalink
Pruning can be a clever way to reduce a model’s resource greediness. But what gets forgotten when you do?
Feedforward Networks for Image Classification Permalink
In the past few months there have been various papers proposing MLP based architectures without Attention or Convolutions. This report analyses the paper ‘Re...
Bringing Back MLPs Permalink
It’s no news that transformers have dominated the field of deep learning ever since 2017. But in their recent work, titled ‘Pay Attention to MLPs,’ Hanxiao L...
Fourier Transform in Neural Networks ??!! Permalink
Continuing on the recent series of reports analyzing newly proposed pure MLP based architectures. In this report I breakdown “FNet Mixing Tokens with Fourier...
Self Supervised Learning
Creating a customer support chatbot using Claude 3, Llamaindex and W&B Weave Permalink
In this tutorial, we will cover how to use the Segment Anything 2 model using the Weights & Biases to log segmentation masks from automatic or prompted m...
VICReg - Variance-Invariance-Covariance Regularization for Self Supervised Learning Permalink
Intuitive and step-by-step guide to understanding the VICReg framework for Self Supervised Learning, along with interactive visualizations and code
DINO - Emerging Properties in Self-Supervised Vision Transformers Permalink
Breakdown of Emerging Properties in Self-Supervised Vision Transformers by Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojan...
Programming
Writing a Training Loop in JAX + FLAX Permalink
A simple end-to-end training and evaluation pipeline in JAX, Flax and Optax.
How to Create a Image Classification Model in JAX/Flax Permalink
Learn how to create a simple image classification model in Flax in this short tutorial complete with code and interactive visualizations.
LLMs
Creating a customer support chatbot using Claude 3, Llamaindex and W&B Weave Permalink
In this article, we’ll go over about how we can create a customer support chatbot using the Claude 3 API, LlamaIndex and W&B Weave.
Chain-of-thought, tree-of-thought, and graph-of-thought - Prompting techniques explained Permalink
In this article, we’ll provide a brief overview of a family of prompting techniques starting with chain-of-thought (CoT), modifying to enable tree search usi...
Agents
Creating a customer support chatbot using Claude 3, Llamaindex and W&B Weave Permalink
In this article, we’ll go over about how we can create a customer support chatbot using the Claude 3 API, LlamaIndex and W&B Weave.