Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Open to Collab
2140.8
TFLOPS
2
2
1
Michal Valko
misovalko
Follow
tahamajs's profile picture
lukbl's profile picture
MTCHA's profile picture
29 followers
·
109 following
https://misovalko.github.io/
misovalko
misovalko
michalvalko
misovalko.bsky.social
AI & ML interests
large language models, reasoning, fine-tuning, test-time computation, reinforcement learning with human feedback, world models
Recent Activity
upvoted
a
paper
13 days ago
A General Theoretical Paradigm to Understand Learning from Human Preferences
authored
a paper
13 days ago
Optimal Design for Reward Modeling in RLHF
authored
a paper
13 days ago
Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms
View all activity
Organizations
misovalko
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a Space
almost 2 years ago
Running
on
Zero
276
Daily Papers
📊
276
Complete list of past Daily Papers