Transformers

Feeds to Scour
SubscribedAll
Scoured 238 posts in 9.1 ms

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

 🔬ML Research  Content type: Academic
arxiv.org·

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

All sorts of famous Attention Layers

 🧠LLMs  Content type: Blog

Why Transformer Models Get Costlier as Context Grows

 🧠LLMs
siliconopera.com·

Geometric Foundations of AI Interpretability

 🧠LLMs
psychologyinaction.org·

The Sequence Knowledge #874: Transformers or Not?

 🤖AI Coding
substackcdn.com··Substack

Deeper Dive: Untangling Tasks in a Toy Transformer

 🤗HuggingFace  Content type: Blog
Less-relevant results

Exploration of a DNA Sequencing Basecaller using Activation Patching

 🧠LLMs
lesswrong.com·

Roommate Therapy with 'Sesame Street's Bert and Ernie

 🤗HuggingFace  Content type: Video
mashable.com·

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

 🔬ML Research  Content type: Tutorial
iwtlp.com··DEV

The Transformer Architecture: A Step-by-Step Guide

 🧠LLMs  Content type: Blog

Dr. Ashish Bamania (@drashishbamania)

 🔬ML Research
substack.com··Substack

DiffusionGemma 26B A4B results on my 5090

 🤗Open Source AI

Transformer-based coreference resolution modeling for Amharic text

 🔍RAG  Content type: Academic
nature.com·

microsoft/LLMLingua: [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

 🔗LangChain  Content type: Code
github.com··DEV

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

 🎵Vibe Coding  Content type: Academic
biorxiv.org·

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

 🎵Vibe Coding
glidemagazine.com·

How LLMs are Actually Trained

 🧠LLMs  Content type: News  Content type: Blog
blog.algomaster.io·

know the mother tongue of your LLMs

 🧠LLMs

How Does Attention Work in LLMs? 2026 Deep Dive

 🧠LLMs  Content type: Blog
medium.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