adamelliotfields (Adam Fields)

upvoted a paper 3 days ago

Searching for Activation Functions

Paper • 1710.05941 • Published Oct 16, 2017 • 1

upvoted an article 5 days ago

Article

2024-04-22 - Hub Incident Post Mortem

By

•

4 days ago

• 15

upvoted an article 7 days ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

8 days ago

• 106

upvoted a paper 12 days ago

U-Net: Convolutional Networks for Biomedical Image Segmentation

Paper • 1505.04597 • Published May 18, 2015 • 5

upvoted a paper 13 days ago

A decoder-only foundation model for time-series forecasting

Paper • 2310.10688 • Published Oct 14, 2023 • 4

upvoted 2 articles about 1 month ago

Article

The Annotated Diffusion Model

Jun 7, 2022

• 21

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18

• 240

upvoted 2 papers about 2 months ago

Mish: A Self Regularized Non-Monotonic Activation Function

Paper • 1908.08681 • Published Aug 23, 2019 • 1

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Paper • 2403.09611 • Published Mar 14 • 119

upvoted a paper 2 months ago

Stealing Part of a Production Language Model

Paper • 2403.06634 • Published Mar 11 • 85

upvoted 8 papers 3 months ago

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Paper • 2402.14905 • Published Feb 22 • 81

upvoted a collection 3 months ago

LLMs

Collection

122 items • Updated 10 days ago • 9

upvoted 13 papers 3 months ago

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Paper • 2101.03961 • Published Jan 11, 2021 • 13

The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Paper • 2101.00027 • Published Dec 31, 2020 • 6

SQuAD: 100,000+ Questions for Machine Comprehension of Text

Paper • 1606.05250 • Published Jun 16, 2016 • 3

GLU Variants Improve Transformer

Paper • 2002.05202 • Published Feb 12, 2020 • 1

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Paper • 1910.01108 • Published Oct 2, 2019 • 10

RoBERTa: A Robustly Optimized BERT Pretraining Approach

Paper • 1907.11692 • Published Jul 26, 2019 • 7

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Paper • 1810.04805 • Published Oct 11, 2018 • 11

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Paper • 1804.07461 • Published Apr 20, 2018 • 4

Attention Is All You Need

Paper • 1706.03762 • Published Jun 12, 2017 • 34

XGBoost: A Scalable Tree Boosting System

Paper • 1603.02754 • Published Mar 9, 2016 • 1

Sequence to Sequence Learning with Neural Networks

Paper • 1409.3215 • Published Sep 10, 2014 • 3

Scikit-learn: Machine Learning in Python

Paper • 1201.0490 • Published Jan 2, 2012 • 1

HiPPO: Recurrent Memory with Optimal Polynomial Projections

Paper • 2008.07669 • Published Aug 17, 2020 • 1

upvoted a collection 4 months ago

papers

Collection

a growing collection of arXiv papers read while learning ML 📜 • 32 items • Updated 3 days ago • 1

upvoted a paper 4 months ago

Deep Residual Learning for Image Recognition

Paper • 1512.03385 • Published Dec 10, 2015 • 5

upvoted a collection 4 months ago

Transformers.js demos

Collection

A collection of my favorite WebML demos, built with Transformers.js! • 23 items • Updated 13 days ago • 35

upvoted 4 papers 4 months ago

Identity Mappings in Deep Residual Networks

Paper • 1603.05027 • Published Mar 16, 2016 • 2

AR-Net: A simple Auto-Regressive Neural Network for time-series

Paper • 1911.12436 • Published Nov 27, 2019 • 1

NeuralProphet: Explainable Forecasting at Scale

Paper • 2111.15397 • Published Nov 29, 2021 • 1

OLMo: Accelerating the Science of Language Models

Paper • 2402.00838 • Published Feb 1 • 74

upvoted a paper 7 months ago

Does GPT-4 Pass the Turing Test?

Paper • 2310.20216 • Published Oct 31, 2023 • 17

Adam Fields

AI & ML interests

Organizations

adamelliotfields's activity

2024-04-22 - Hub Incident Post Mortem

PaliGemma – Google's Cutting-Edge Open Vision Language Model

The Annotated Diffusion Model

Welcome Llama 3 - Meta's new open LLM