Papers I Read Notes and Summaries

Toolformer - Language Models Can Teach Themselves to Use Tools

10 Feb 2023

Introduction

  • The paper presents Toolformer, a language model that uses simple APIs...

Synthesized Policies for Transfer and Adaptation across Tasks and Environments

29 Mar 2021

Introduction

  • The paper studies transfer learning in RL, focusing on simultaneous transfer...

Deep Neural Networks for YouTube Recommendations

22 Mar 2021

Introduction

  • The paper describes YouTube’s deep learning-based recommendation system.

  • Continue reading -->

The Tail at Scale

15 Mar 2021

Introduction

  • The paper presents some causes for (temporary) high-latency episodes in large-scale...

Practical Lessons from Predicting Clicks on Ads at Facebook

08 Mar 2021

Introduction

  • The paper describes several design choices for developing a model for...

Ad Click Prediction - a View from the Trenches

01 Mar 2021

Introduction

  • The paper presents case studies from the experience of deploying an...

Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics

22 Feb 2021

Introduction

  • The paper studies the effect of catastrophic forgetting on representations in...

When Do Curricula Work?

15 Feb 2021

Introduction

  • The paper systematically investigates when does curriculum learning help.

  • ...

Continual learning with hypernetworks

08 Feb 2021

Introduction

  • The paper proposes the use of task-conditioned HyperNetworks for lifelong...

Zero-shot Learning by Generating Task-specific Adapters

01 Feb 2021

Introduction

  • The paper introduces HYPTER - a framework for zero-shot learning (ZSL)...