Transformers

Feeds to Scour
SubscribedAll
Scoured 274 posts in 7.4 ms

markusheimerl/gpt: A generative pretrained transformer implementation

 🧠LLMs  Content type: Code
github.com··Hacker News

Reachability and asymptotics of Gaussian Transformer dynamics

 💬Natural Language Processing  Content type: Academic
arxiv.org·

Dr. Ashish Bamania (@drashishbamania)

 🔬Deep Learning
substack.com··Substack

OCOO-T : A SIMPLE AND SCALABLE VIRTUAL CELL MODEL FOR TRANSCRIPTIONAL PERTURBATION RESPONSE PREDICTION

 🎯Fine-tuning  Content type: Academic
biorxiv.org·

know the mother tongue of your LLMs

 🤖LLM

2026-06-06

 📈Optimization
florian.photo·

Lightweight CNN SE transformer for robust weed classification with optimizer aware performance

 🧠Neural Networks  Content type: Academic
nature.com·

ELI5 is a terrible learning prompt, here's the structural reason it fails and a 4-level replacement that actually sticks

 🧠LLMs  Content type: Blog  Content type: Tutorial

Your LLM Isn’t Reading Your Manners — It’s Counting Your Tokens

 🧠LLM Inference  Content type: Blog
medium.com
·

Attention Based Interpretability With Concept Transformer

 🤖Machine Learning  Content type: Blog
medium.com
·

The Transformer Architecture: A Step-by-Step Guide

 🔬Deep Learning  Content type: Blog

The Sequence Knowledge #874: Transformers or Not?

 🧠Neural Networks
substackcdn.com··Substack

Why LLMs hallucinate?

 🤖Data science  Content type: Blog
medium.com
·

Visual Artist and Percussionist Bob Bert (Sonic Youth, Pussy Galore) Talks Experimenting With Sounds on Debut Solo Album ‘Beach Bongo Bloodbath’ (INTERVIEW)

 📔Journaling
glidemagazine.com·

The Transformer, Demystified — Let's Actually Build One

 🧠Neural Networks  Content type: News
mlwhiz.com
·

Machine learning from scratch, what to build before using scikit-learn

 🧠Neural Networks  Content type: Tutorial
iwtlp.com··DEV

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

 🤖Machine Learning  Content type: Academic
arxiv.org·
Less-relevant results

The 400-Millisecond History: How Seventy Years of AI Built Modern Advertising

 🤖Machine Learning
iabtechlab.com·

Google open-sources speedy DiffusionGemma text diffusion model

 💬Natural Language Processing
siliconangle.com·

You Can Get a 48V 400W Adult Electric Bike With 20MPH Top Speed and 32 Mile Range For Less Than $160 With Free Shipping

 Electronics
ign.com·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help