Post-training

Feeds to Scour
SubscribedAll
Scoured 154 posts in 6.5 ms

My research agenda and work

 🧠AI
lesswrong.com·

Alignment Defends LLMs from Property Inference Attacks

 🧠AI  Content type: Academic
arxiv.org·
Less-relevant results

How Will the Multimodal AI Market Grow Through 2034 Amid Emerging Trends and Business Strategies?

 💬LLMs  Content type: Blog

TAHOE: Text-to-SQL with Automated Hint Optimization from Experience

 💬LLMs  Content type: Academic
arxiv.org·

The sample efficiency black hole

 🏋️Pretraining  Content type: News
dwarkesh.com··Hacker News

(Mis)generalization of Helpful-Only Fine-tuning

 🌐World Models
lesswrong.com·

Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching

 💬LLMs  Content type: Academic
arxiv.org·

EDPB meets with EU Commissioner McGrath and adopts common data breach notification template

 💻Software Engineering
edpb.europa.eu·

magenta/magenta-realtime: Magenta RealTime 2: An Open-Weights Live Music Model

 💬LLMs  Content type: Code
github.com·

Can You Hide From a Natural Language Autoencoder?

 🏋️Pretraining  Content type: Blog
yogesh.bearblog.dev·

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

 🎮RL  Content type: Academic
arxiv.org·

Raize Orion Multi-framework GRC with anchored NIS2 reporting clocks

 💬LLMs
raizehq.dev··Hacker News

PriFT: Prior-Support Guided Supervised Fine-Tuning

 🌐World Models  Content type: Academic
arxiv.org·

Training Deliberative Monitors for Black-Box Scheming Detection

 🌐World Models
lesswrong.com·

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

 💬LLMs  Content type: Academic
arxiv.org·

We Should Take Text Optimization More Seriously

 💬LLMs  Content type: Blog
yoonholee.com··Hacker News

Multilingual Refusal Alignment for Safer Large Language Models

 💬LLMs  Content type: Academic
arxiv.org·

Optimisation over non-stationary distributions creates weirder minds

 🌐World Models
lesswrong.com·

The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

 🧠AI  Content type: Academic
arxiv.org·

Job Searcher

 💬LLMs  Content type: Blog
huggingface.co·
Sign up or log in to see more results

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