
Latest
Mar
25

How Phi-4 Cracked Small Multimodality
Phi-4 extends the existing Phi model’s capabilities by adding vision and audio all in the same model. This means
8 min read
Mar
05

Training a Rust 1.5B Coder LM with Reinforcement Learning (GRPO)
Group Relative Policy Optimization (GRPO) has proven to be a useful algorithm for training LLMs to reason and improve on
17 min read
Feb
11

Why GRPO is Important and How it Works
Last week on Arxiv Dives we dug into research behind DeepSeek-R1, and uncovered that one of the techniques they use
12 min read
Feb
05

🧠 GRPO VRAM Requirements For the GPU Poor
Since the release of DeepSeek-R1, Group Relative Policy Optimization (GRPO) has become the talk of the town for Reinforcement Learning
9 min read
Feb
04

How DeepSeek R1, GRPO, and Previous DeepSeek Models Work
In January 2025, DeepSeek took a shot directly at OpenAI by releasing a suite of models that “Rival OpenAI’s
15 min read
Jan
29

No Hype DeepSeek-R1 Reading List
DeepSeek-R1 is a big step forward in the open model ecosystem for AI with their latest model competing with OpenAI&
27 min read
Jan
27

Oxen v0.25.0 Migration
Today we released oxen v0.25.0 🎉 which comes with a few performance optimizations, including how we traverse the Merkle
3 min read
Jan
27

🌲 Merkle Tree VNodes
In this post we peel back some of the layers of Oxen.ai’s Merkle Tree and show how we
8 min read
Jan
27

🌲 Merkle Tree 101
Intro
Merkle Trees are important data structures for ensuring integrity, deduplication, and verification of data at scale. They are used
9 min read
Jan
21

arXiv Dive: RAGAS - Retrieval Augmented Generation Assessment
RAGAS is an evaluation framework for Retrieval Augmented Generation (RAG). A paper released by Exploding Gradients, AMPLYFI, and CardiffNLP. RAGAS
13 min read