Homepage
Open in app
Sign in
Get started
Yugen.ai Technology Blog
Engineering, Machine Learning & AI
Follow
Real Time Fraud Detection Using Apache Flink — Part 2
Real Time Fraud Detection Using Apache Flink — Part 2
Detect suspicious transactions using complex event patterns
Yugen.ai
Feb 23
Understanding the Math Behind GRPO — DeepSeek-R1-Zero
Understanding the Math Behind GRPO — DeepSeek-R1-Zero
The Policy Optimisation algo in DeepSeekMath & DeepSeek’s first gen reasoning models.
Yugen.ai
Feb 6
Real Time Fraud Detection Using Apache Flink — Part 1
Real Time Fraud Detection Using Apache Flink — Part 1
A simple Flink application to detect suspicious transactions
Yugen.ai
Feb 5
Driving Faster Time to Value in Fraud Detection — A CRO Guide
Driving Faster Time to Value in Fraud Detection — A CRO Guide
Strategic Guide for CROs to Accelerate Fraud Detection ROI
Yugen.ai
Feb 4
Breaking Down Words: Byte Pair Encoding
Breaking Down Words: Byte Pair Encoding
Learn BPE by training from scratch
Yugen.ai
Feb 3
Understanding Spark’s Catalyst Optimiser
Understanding Spark’s Catalyst Optimiser
How advanced programming language features are used to build an extensible query optimiser in Spark
Yugen.ai
Jan 13
DeepSeek-V3 — Advances in MoE Load Balancing and Multi-Token Prediction Training
DeepSeek-V3 — Advances in MoE Load Balancing and Multi-Token Prediction Training
By Soumanta Das
Yugen.ai
Jan 4
Evaluating Chain of Density Method for Better LLM Summarization
Evaluating Chain of Density Method for Better LLM Summarization
By Deepak Jangra, Akshay Singh
Deepak Jangra
Sep 12, 2024
Navigating Indeterminism: Improving Reproducibility in LLMs
Navigating Indeterminism: Improving Reproducibility in LLMs
Deepak Jangra
Aug 30, 2024
LLM Model Composition from scratch
LLM Model Composition from scratch
A simplified implementation of Google Research & Google DeepMind’s CALM (Composition to Augment Language Models) paper
Yugen.ai
Aug 18, 2024
Exploring GraphRAG: Improving Retrieval in RAGs — Part 1
Exploring GraphRAG: Improving Retrieval in RAGs — Part 1
This is a multi-part series involving different explorations done to understand the potential of GraphRAGs. This is the first part, where…
Kanishk Tyagi
Aug 14, 2024
Unlocking Financial Insights: RAGs for Precise Information Retrieval from 10-K reports
Unlocking Financial Insights: RAGs for Precise Information Retrieval from 10-K reports
By Deepak Jangra, Akshay Singh
Yugen.ai
Aug 13, 2024
Introducing CansoAI Platform
Introducing CansoAI Platform
Platform to accelerate ML Systems development & decisioning
Kumar Sanjog
Jul 18, 2024
Efficient LLM Fine-Tuning: LoRA, DoRA, and Apple’s Innovative Approach
Efficient LLM Fine-Tuning: LoRA, DoRA, and Apple’s Innovative Approach
Understanding the impact of LoRA Adapters and breaking down the Model adaptation optimization techniques to enhance the ability of…
Yugen.ai
Jun 23, 2024
AI Risks: Strategic Shifts Businesses are Making
AI Risks: Strategic Shifts Businesses are Making
Fraud prevention amongst the top priorities for industry leaders
Kumar Sanjog
Apr 26, 2024
Achieving a 6x improvement in Data Ingestion in Imply
Achieving a 6x improvement in Data Ingestion in Imply
Running the (experimental) Multi-Stage Query Ingestion in Production
Yugen.ai
Apr 3, 2024
How to Build a Real-time Fraud Prevention System
How to Build a Real-time Fraud Prevention System
A guide to fraud prevention using Machine Learning
Kumar Sanjog
Apr 2, 2024
RAFT — RAGs Meet Fine-Tuning
RAFT — RAGs Meet Fine-Tuning
RAFTs (Retrieval-Augmented Fine-Tuning) combine strengths of RAGs and Domain Specific Fine-tuning to better adapt pre-trained LLMs for…
Yugen.ai
Mar 31, 2024
Optimise Cloud Composer 1 Costs — From $188/day to $11/day
Optimise Cloud Composer 1 Costs — From $188/day to $11/day
Introduction
Yugen.ai
Feb 14, 2024
Yugen.ai Turns One
Yugen.ai Turns One
Learnings from 2020 and Predictions for 2021
Yugen.ai
Jan 6, 2021
About Yugen.ai Technology Blog
Latest Stories
Archive
About Medium
Terms
Privacy
Teams