Model Training

Feeds to Scour
SubscribedAll
Scoured 844 posts in 22.6 ms

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

 📉Deep Learning  Content type: Academic
arxiv.org·

Inferoa AI harness claimed 90% cache savings. We ran it and measured 97.8%

 🔥PyTorch

KJLdefeated/RL.cu: RLVR training for LLM in CUDA/C++

 🖥️ML Systems  Content type: Code
github.com··Hacker News

Fine-tuning Large Language Models (LLMs) using PEFT

 📉Deep Learning  Content type: Blog
medium.com
·

How to reduce capability degradation from off-model SFT

 💬LLMs
lesswrong.com·

Finetuning masking challenges narrow-task evaluation of cell foundation models

 💬LLMs  Content type: Academic
biorxiv.org·

If Algorithms Are Your Arsenal, Parameters Are Your Best Weapon

 📐Scaling Laws  Content type: Blog
medium.com
·

Train Models Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell

 💬LLMs  Content type: News  Content type: Blog
developer.nvidia.com·

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

 📉Deep Learning  Content type: Tutorial
iwtlp.com··DEV

Backpropagation Without the Magic: A First-Principles Derivation

 📉Deep Learning  Content type: Blog
medium.com
·

Introducing North Mini Code: Cohere’s First Model For Developers

 🔄Transformers  Content type: Blog

DiffusionGemma: The Developer Guide

 🖥️ML Systems  Content type: Blog

NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI

 💬LLMs  Content type: Blog
blogs.nvidia.com·

The Era of System 2 AI

 🤖AI Agents  Content type: Blog
medium.com
·

DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200

 🖥️ML Systems  Content type: News

A new chapter of efficient foundation models for medical imaging

 🖥️ML Systems

New comment by bkjlblh in "Claude Fable 5"

 💬LLMs  Content type: Discussion

New comment by perturbation in "Ask HN: Who wants to be hired? (June 2026)"

 📉Deep Learning

Generalizable self-supervised learning for imaging flow cytometry on multi-dataset leukocyte differential

 📉Deep Learning  Content type: Academic
nature.com·

2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash, and MTP

 💬LLMs  Content type: Blog
dnhkng.github.io·

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