Mathy AI Substack
Subscribe
Sign in
Home
Notes
Archive
About
The Complexity Dynamics of Grokking
Mike’s Daily Paper Review – April 30, 2025
May 1, 2025
•
Mike Erlihson, Mathy AI
7
2
1
Latest
Top
Discussions
The "RAG" of Time Series Analysis
RAFT: Retrieval-Augmented Time Series Forecasting, Andrey and Mike’s Daily Paper, 17.01.26
Jan 17
•
Mike Erlihson, Mathy AI
and
Andrey Finkelshtein
2
1
The Transformer Goes on (Latent) Leave
The Free Transformer, Mike’s Daily Paper Review: 14.01.26
Jan 15
•
Mike Erlihson, Mathy AI
1
1
The SSL Wars: Provable Benefits for the Joint Embedding Approach
Joint-Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self-Supervised Learning; Niv and Mike’s Daily Paper 12.01.26
Jan 12
•
Mike Erlihson, Mathy AI
and
Niv Cohen
3
1
Loop Within a Loop: Why Reasoning Models Get Stuck and How Learning Errors Drive This
Mike’s Daily Paper 11.01.26; WAIT, WAIT, WAIT... WHY DO REASONING MODELS LOOP?
Jan 11
•
Mike Erlihson, Mathy AI
1
Epiplexity: When Computation Creates Information
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence, Mike’s daily paper review: 09.01.26
Jan 9
•
Mike Erlihson, Mathy AI
4
Training Large Language Models with Curriculum Learning (2020-2025)
By Dr. Mike Erlihson and Dr. Barak Or
Jan 8
•
Mike Erlihson, Mathy AI
and
Barak Or
4
Are Small Language Models the Future of Agentic AI?
Michael & Mike’s Daily Paper, 07.01.26, Small Language Models are the Future of Agentic AI
Jan 7
•
Mike Erlihson, Mathy AI
and
Michael Orlovsky
3
See all
Mathy AI Substack
Deep learning paper reviews, blogs about machine learning techniques, LLM discussions
Subscribe
Recommendations
View all 11
AI by Hand ✍️
Prof. Tom Yeh
Ahead of AI
Sebastian Raschka, PhD
The AiEdge Newsletter
Damien Benveniste
💎DiamantAI
Nir Diamant
Deep (Learning) Focus
Cameron R. Wolfe, Ph.D.
Mathy AI Substack
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
