My Medium Info
Top Writers
Get Your Portfolio
Dr. Ashish Bamania
~ Boosted Medium Articles ~
Overall Stats
Boosted Articles
62
Total Views
583,040
Total Reads
250,148
Read Ratio
42.9%
Total Claps
44,856
Total Comments
833
Avg. claps per article
723
Avg. comments per article
13
Proximal SFT: SFT Supercharged By RL Is Here
Deep dive and learn about Proximal SFT, a new algorithm that combines SFT with PPO, leading to improved post-training performance of LLMs.
1,002 views
‧
423 reads
‧
42.22%
machine-learning
Sep 05, 2025
Sep 06, 2025
All The Basics That You Need To Know About LLMs
We're living in an amazing time where understanding AI can open so many doors. Learning about LLMs might be you smartest investment today.
14,071 views
‧
5,179 reads
‧
36.81%
artificial-intelligence
machine-learning
Aug 24, 2025
Aug 30, 2025
R-Zero: A Method For Training Reasoning LLMs With Zero Data Is Here
A deep dive into the R-Zero framework that helps LLMs self-evolve to get better at reasoning without using any external training data.
6,757 views
‧
3,093 reads
‧
45.77%
artificial-intelligence
machine-learning
Aug 16, 2025
Aug 16, 2025
Hierarchical Reasoning Model: An AI Architecture That Beats OpenAI's 'o3-mini-high' Is Here
A deep dive into the Hierarchical Reasoning Model, an AI architecture that outperforms powerful reasoning models available to us today.
10,471 views
‧
5,073 reads
‧
48.45%
Aug 10, 2025
Aug 10, 2025
An Easy-To-Follow Introduction To The CNOT Gate
It's time to learn about Multi-qubit quantum gates, starting with the CNOT gate.
1,076 views
‧
433 reads
‧
40.24%
math
programming
Jul 26, 2025
Jul 28, 2025
Model Context Protocol Isn't Confusing If You Understand It This Way
Take a deep dive into how the Model Context Protocol (MCP) works and solidify your understanding by building an agentic system that uses...
70,025 views
‧
12,598 reads
‧
17.99%
programming
Jul 25, 2025
Jul 25, 2025
You Don't Need Normalization In Transformers Anymore
A deep dive into the internals of Layer Normalization, and how Dynamic Tanh can fully replace it in Transformers with no performance loss.
4,104 views
‧
1,921 reads
‧
46.81%
machine-learning
Jul 21, 2025
Jul 21, 2025
LLMs Can Now Self-Evolve At Test Time Using Reinforcement Learning
A deep dive into Test-Time Reinforcement Learning (TTRL), a technique that allows LLMs to learn from unlabelled test-time data using RL.
7,350 views
‧
3,034 reads
‧
41.28%
artificial-intelligence
machine-learning
Jul 16, 2025
Jul 16, 2025
Microsoft Reveals Its Path To Medical Superintelligence
A deep dive into Microsoft's 'SDBench' and 'MAI-DxO', to explore what they mean for the future of clinicians and medical AI.
1,876 views
‧
897 reads
‧
47.81%
artificial-intelligence
health
Jul 09, 2025
Jul 09, 2025
LLMs Fail Embarrassingly At Newer Ways Of Testing Understanding
A deep dive into Potemkin understanding in LLMs, why current benchmarks miss it, and why it matters for measuring true understanding in...
4,902 views
‧
2,250 reads
‧
45.9%
artificial-intelligence
machine-learning
Jul 02, 2025
Jul 02, 2025
LLMs Can Now Be Pre-Trained Using Pure Reinforcement Learning
A deep dive into Reinforcement Pre-Training (RPT), a new technique introduced by Microsoft researchers to scalably pre-train LLMs using RL.
15,460 views
‧
6,517 reads
‧
42.15%
artificial-intelligence
machine-learning
Jun 26, 2025
Jun 26, 2025
Darwin-Gödel Machine: The First Self-Improving AI System Is Here
A deep dive into the novel architecture of the Darwin-Gödel Machine and what its self-improvement capability means for the future of AI.
11,590 views
‧
5,807 reads
‧
50.1%
artificial-intelligence
Jun 23, 2025
Jun 23, 2025
Apple's New Research Shows That LLM Reasoning Is Completely Broken
A deep dive into Apple research that exposes the flawed thinking process in state-of-the-art Reasoning LLMs
13,589 views
‧
7,266 reads
‧
53.47%
artificial-intelligence
machine-learning
data-science
Jun 08, 2025
Jun 08, 2025
Build A Quantum Circuit Using Single-Qubit Quantum Gates With Qiskit
Learn to manipulate qubits using single-qubit quantum gates in this lesson.
1,044 views
‧
401 reads
‧
38.41%
programming
Jun 05, 2025
Jun 07, 2025
Your Vector Databases Aren't Safe Anymore
A deep dive into the 'Vec2Vec' method that can translate embeddings from unknown encoders and decode them to extract sensitive information.
3,655 views
‧
1,872 reads
‧
51.22%
machine-learning
May 30, 2025
May 30, 2025
A Simple Principle From Noise-Cancelling Headphones Supercharges Transformers Like Never Before
A deep dive into the Differential Transformer architecture, learning how it works & why it is such a promising architecture to advance...
3,764 views
‧
1,944 reads
‧
51.65%
machine-learning
May 24, 2025
May 24, 2025
AI Just Made Data Compression Algorithms Multiple Times Better Than Ever
A deep dive into the 'LMCompress' algorithm that outperforms all traditional algorithms, supercharging data compression like never before.
4,628 views
‧
2,840 reads
‧
61.37%
machine-learning
data-science
May 20, 2025
May 20, 2025
You Don't Need 'Thinking' In LLMs To Reason Better
Deep dive and learn about the novel 'NoThinking' method that bypasses thinking in conventional reasoning LLMs to supercharge them.
1,220 views
‧
579 reads
‧
47.46%
artificial-intelligence
machine-learning
May 13, 2025
May 13, 2025
A Hands-On Guide To Federated Machine Learning With 'Flower'
A deep dive into Federated Learning and training an ML model to detect eye diseases using the Flower framework.
1,355 views
‧
532 reads
‧
39.26%
machine-learning
May 05, 2025
May 05, 2025
You Don't Need Backpropagation To Train Neural Networks Anymore
A deep dive into the 'NoProp' algorithm that eliminates the need for Forward pass and Backpropagation and coding it up from scratch.
59,008 views
‧
25,447 reads
‧
43.12%
machine-learning
Apr 25, 2025
Apr 25, 2025
Building A LinkedIn Content Creation Agency Using Google's Agent Development Kit
A hands-on tutorial on creating a helpful content creation multi-agent AI system using Google's Agent Development Kit (ADK)
4,333 views
‧
1,740 reads
‧
40.16%
programming
Apr 17, 2025
Apr 18, 2025
A Practical Guide To Fast Fine-Tuning Your LLMs With Unsloth
Learn to Fine-tune Llama 3 in minutes for medical question-answering with Unsloth using QLoRA
5,138 views
‧
1,998 reads
‧
38.89%
machine-learning
Apr 11, 2025
Apr 11, 2025
Building Your First Agentic RAG From The Ground Up
Learn to build a Multi-agentic RAG system by coding up Agentic tools and a Vector database from scratch.
5,868 views
‧
1,947 reads
‧
33.18%
machine-learning
programming
Apr 07, 2025
Apr 07, 2025
Your First Hands-on Guide To Quantum Programming With Qiskit
From mathematics to code, here's everything that you need to know to write and run your first Quantum program on an IBM Quantum computer.
1,584 views
‧
620 reads
‧
39.14%
Mar 30, 2025
Mar 31, 2025
Your First Hands-On Lesson On Using AlphaFold
A practical lesson on folding proteins using AlphaFold (and more!)
1,067 views
‧
405 reads
‧
37.96%
machine-learning
Mar 24, 2025
Mar 24, 2025
Building Your First AI Agent (That Will Actually Improve You As An AI Engineer)
A guide to building a helpful Multi-agent AI system that helps you find the top 10 AI research papers published in ArXiv every day
54,800 views
‧
20,060 reads
‧
36.61%
artificial-intelligence
programming
Mar 17, 2025
Mar 17, 2025
Revisiting The Basics: Rotary Position Embeddings (RoPE)
A lesson on Positional Embeddings all the way up to Rotary Position Embeddings (RoPE) from the ground up.
2,861 views
‧
1,392 reads
‧
48.65%
machine-learning
Mar 16, 2025
Mar 16, 2025
'FANformer' Is The New Game-Changing Architecture For LLMs
A deep dive into how FANFormer architecture works and what makes it so powerful compared to Transformers
4,662 views
‧
2,622 reads
‧
56.24%
machine-learning
Mar 09, 2025
Mar 10, 2025
The Open Source "Agentic Reasoning" Beats Google Gemini Deep Research
A deep dive into the "Agentic Reasoning" framework & the techniques behind it that make it outperform the most advanced reasoning LLMs...
7,341 views
‧
3,793 reads
‧
51.67%
machine-learning
programming
Feb 19, 2025
Feb 19, 2025
Multi-Head Latent Attention Is The Powerful Engine Behind DeepSeek
A deep dive Into DeepSeek's innovative Attention mechanism that makes its LLMs so good
6,206 views
‧
2,211 reads
‧
35.63%
Feb 14, 2025
Feb 14, 2025
DeepSeek-R1 Beats OpenAI's o1, Revealing All Its Training Secrets Out In The Open
A deep dive into how DeepSeek-R1 was trained from scratch and how this open-source research will accelerate AI progress like never before.
21,938 views
‧
11,210 reads
‧
51.1%
artificial-intelligence
machine-learning
Jan 27, 2025
Jan 27, 2025
Memory Layers Are Supercharging LLMs Like Never Before
A deep dive into how Memory layers work and how they supercharge the performance of LLMs.
11,746 views
‧
5,729 reads
‧
48.77%
machine-learning
Jan 21, 2025
Jan 21, 2025
Do LLMs Really Understand Math? No.
A deep dive into the latest research showing that current leading AI models are not capable of understanding and solving maths.
2,026 views
‧
960 reads
‧
47.38%
math
programming
Dec 15, 2024
Dec 15, 2024
Fourier Analysis Networks (FANs) Are Here To Break Barriers In AI
A deep dive into Fourier Analysis Networks (FANs), a novel neural network architecture and learning to build one from scratch.
25,399 views
‧
12,631 reads
‧
49.73%
machine-learning
Dec 06, 2024
Dec 06, 2024
Vision Transformers Completely Redefine How AI Perceives The Real World
A deep dive into the Vision Transformer (ViT) architecture that transformed Computer Vision and learning to build one from scratch
1,723 views
‧
759 reads
‧
44.05%
machine-learning
Nov 18, 2024
Nov 18, 2024
XNets Are Here To Outcompete MLPs & KANs
Deep dive into XNets, a neural network architecture that outperforms MLPs, KANs, and PINNs and learn to build one from scratch.
5,942 views
‧
3,180 reads
‧
53.52%
machine-learning
Nov 11, 2024
Nov 12, 2024
Amazing Things Happen When Attention Heads Are Supercharged Using Mixture-Of-Experts
A deep dive into how Mixture-of-Head Attention (MoH) enhances Attention mechanisms, making existing LLMs more efficient than ever.
2,017 views
‧
847 reads
‧
41.99%
machine-learning
programming
Oct 28, 2024
Oct 28, 2024
We Have Finally Found A Solution To An Extremely Energy Efficient AI
A deep dive into the L-Mul/ Linear complexity multiplication algorithm that makes our existing AI models faster and super energy-efficient
2,809 views
‧
1,304 reads
‧
46.42%
programming
Oct 21, 2024
Oct 22, 2024
'MathPrompt' Embarassingly Jailbreaks All LLMs Available On The Market Today
A deep dive into how 'MathPrompt' works, why it is so effective, and why it needs early patching to prevent harmful LLM content generation
19,341 views
‧
11,690 reads
‧
60.44%
artificial-intelligence
machine-learning
Sep 25, 2024
Sep 25, 2024
'Transfusion' Is Supercharging Training Multi-Modal LLMs Like Never Before
A deep dive into how 'Transfusion' enables training a single Transformer model using text & images to create a powerful multi-modal LLM
2,590 views
‧
1,030 reads
‧
39.77%
machine-learning
Sep 17, 2024
Sep 17, 2024
A Human Brain Inspired RAG Approach Has Reached The New State-of-the-Art
A deep dive into 'HippoRAG' — a faster, cheaper, and better-performing framework inspired by long-term human memory
5,769 views
‧
2,824 reads
‧
48.95%
machine-learning
programming
Sep 04, 2024
Sep 04, 2024
Google's New AI Can Hallucinate An Entire Video Game In Real Time Without A Game Engine
A deep dive into how Google's 'GameNGen' model works, how it is trained, and how it opens up new avenues for future AI applications.
5,017 views
‧
2,494 reads
‧
49.71%
artificial-intelligence
machine-learning
Aug 29, 2024
Aug 30, 2024
'MedGraphRAG' Is A Complete Game Changer For AI In Medicine
A deep-dive into how RAG, GraphRAG, and MedGraphRAG work and how they significantly improve the performance of LLM responses in Medicine.
6,000 views
‧
2,732 reads
‧
45.53%
data-science
programming
Aug 22, 2024
Aug 22, 2024
'Skeleton Recall Loss' Is The New Breakthrough In Segmentation
A deep dive into how Segmentation works and how the new Skeleton Recall Loss sets itself as the new state-of-the-art in this process
2,603 views
‧
1,042 reads
‧
40.03%
machine-learning
Aug 06, 2024
Aug 07, 2024
An LLM With A Visual Sketchpad Can Now Smash Its Competitors Without One (Even GPT-4o)
A deep dive into the "Sketchpad" framework that enables LLMs to draw and reason via the "Visual Chain-of-Thought Prompting" approach
1,362 views
‧
549 reads
‧
40.31%
machine-learning
programming
Jul 20, 2024
Jul 21, 2024
Here Is Google DeepMind's New Research To Build Massive LLMs With A Mixture Of Million Experts
A deep dive into the the Mixture-of-a-Million-Experts (MoME) architecture, which outperforms traditional LLMs like never before
4,327 views
‧
2,066 reads
‧
47.75%
machine-learning
Jul 13, 2024
Jul 13, 2024
The New 'Adam-mini' Optimizer Is Here To Cause A Breakthrough In AI
A deep dive into how Optimizers work, their developmental history, and how the 'Adam-mini' optimizer enhances LLM training like never...
4,736 views
‧
2,371 reads
‧
50.06%
machine-learning
Jul 05, 2024
Jul 05, 2024
A Squad Of Open-Source LLMs Can Now Beat OpenAI's Closed-Source GPT-4o
A deep dive into how the Mixture-of-Agents (MoA) model leverages the collective strengths of multiple open-source LLMs and beats GPT-4o
17,145 views
‧
5,525 reads
‧
32.23%
artificial-intelligence
machine-learning
Jun 30, 2024
Jun 30, 2024
Kolmogorov-Arnold Networks (KANs) Are Being Used To Boost Graph Deep Learning Like Never Before
A deep dive into how Graph Kolmogorov-Arnold Networks (GKANs) are improving Graph Deep Learning to surpass traditional approaches
7,884 views
‧
3,297 reads
‧
41.82%
machine-learning
Jun 26, 2024
Jun 26, 2024
Superfast Matrix-Multiplication-Free LLMs Are Finally Here
A deep dive into Matrix-Multiplication-Free LLMs that might drastically decrease the use of GPUs in AI, unlike today
12,585 views
‧
6,332 reads
‧
50.31%
machine-learning
Jun 20, 2024
Jun 20, 2024
Bend — A Rust-Backed Language That Supercharges Parallel Computing Like Never Before
A programming language that feels like Python and scales like CUDA, without needing any effort to make your code parallel, is here.
11,044 views
‧
4,807 reads
‧
43.53%
programming
May 18, 2024
May 19, 2024
A Deep Dive into SHA-256 By Learning To Hash by Hand
A thorough exploration of the fundamental details of the algorithm that preserves the security of today's computer systems
4,616 views
‧
1,746 reads
‧
37.82%
programming
May 14, 2024
May 14, 2024
Kolmogorov-Arnold Networks (KANs) Might Change AI As We Know It, Forever
A Deep Dive Into How Kolmogorov-Arnold Networks Work, How They Differ From Multi-Layer Perceptrons & How To Train One From Scratch
27,505 views
‧
12,807 reads
‧
46.56%
machine-learning
May 07, 2024
May 08, 2024
The Story Of The "Morris Worm" & How Rust Could Have Prevented It
A Deep Dive Into How How Cutting Down On C/ C++ And Widespread Adoption Of Rust Can Save Critical Systems That Humans Use Every Day
2,343 views
‧
1,248 reads
‧
53.27%
cybersecurity
programming
Apr 29, 2024
May 01, 2024
AI Can Now Look At Your Heart & Predict How Long You'll Live.
A Deep Dive Into How The Heart Works And How An AI Model Can Predict Human Survival Using Cardiac Images
2,351 views
‧
1,062 reads
‧
45.17%
artificial-intelligence
Apr 21, 2024
Apr 23, 2024
Stable Signature: Meta's Solution To End Misinformation Spread With AI-Generated Images
A Deep Dive Into How Generative AI Works, How It Can Be Used To Spread Misinformation & How It Is Being Fixed
1,608 views
‧
789 reads
‧
49.07%
artificial-intelligence
machine-learning
Apr 15, 2024
Apr 16, 2024
AI Can Now 'See' What You're Thinking About. This Is How Engineers At Meta Made It Possible.
A Deep Dive Into The AI That Can Generate Images From Brain Recordings In Real-time
1,798 views
‧
802 reads
‧
44.61%
artificial-intelligence
machine-learning
Apr 07, 2024
Apr 08, 2024
AI Is Now Treating Cancer (And This Begins An Exciting Era For Modern Medicine)
A Deep Dive Into How AI Helped Humans Discover A Novel Drug That Treats Liver Cancer
2,629 views
‧
1,181 reads
‧
44.92%
artificial-intelligence
science
health
Mar 28, 2024
Mar 29, 2024
AI Is Discovering New Antibiotics — A Task Previously Deemed Extremely Challenging For Humans.
A Deep Dive Into How AI Helped Humans Discover Two New Antibiotics — 'Halicin' & 'Abaucin'
2,924 views
‧
1,494 reads
‧
51.09%
health
Mar 18, 2024
Mar 19, 2024
Hold Tight, Nuclear Fusion Is Coming Sooner Than You Think (Thanks To Artificial Intelligence!)
A Deep Dive Into How AI Is Being Used To Make Nuclear Fusion Possible
2,981 views
‧
1,839 reads
‧
61.69%
artificial-intelligence
science
Feb 28, 2024
Feb 29, 2024
Google Grants $1 Million To Move From C++ To Rust. Is C++ Slowly Dying?
Google Is (Early) Adopting Rust. Are You?
24,304 views
‧
15,888 reads
‧
65.37%
programming
Feb 08, 2024
Feb 09, 2024
AI Is Breaking Past Human Discoveries.
Taking a deep dive into AlphaDev and exploring how it is discovering novel groundbreaking algorithms in Computer Science
5,171 views
‧
3,019 reads
‧
58.38%
artificial-intelligence
programming
Dec 12, 2023
Dec 12, 2023