Akshat Gupta

Generative modeling is currently one of the most thrilling domains in deep learning research. Traditional models like Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) have already demonstrated impressive capabilities in synthetically generating realistic data, such as images and text. However, diffusion models is swiftly gaining prominence as a powerful model in the arena of high-quality and stable generative modeling. This blog explores diffusion models, examining their operational mechanisms, architectural designs, training processes, sampling methods, and the key advantages that position them at the forefront of generative AI. ...

As machine learning systems are increasingly used in critical areas like finance, employment, and criminal justice, it’s essential to ensure these models are fair and do not discriminate against certain groups. In this post, I will explore the concept of fairness in machine learning. Related discussions on algorithmic accountability often draw on tools such as HuggingFace model cards, which document bias evaluations for publicly released models. Defining Fairness Fairness in machine learning can be understood in several ways: ...

If you’ve been working with modern AI systems — particularly in the realm of Large Language Models (LLMs), image embeddings, or recommendation engines — you’ve probably heard of vector databases. But what are they really? And why is everyone in the ML community suddenly so excited about them? Let me break it down in simple terms, along with how I’ve been exploring them in my own projects. 🔍 The Problem: Why Traditional Databases Fall Short Traditional databases (like PostgreSQL or MongoDB) are great when you’re dealing with exact matches or relational queries: ...

If you’re working with knowledge graphs, one term that keeps popping up is ontology. Sounds academic, right? Like something you’d find buried in a philosophy textbook. But in the world of AI, data science, and search engines, an ontology is far from abstract — it’s the blueprint that gives your knowledge graph meaning. Let’s break it down and explore how it all fits together. 🧠 What Is an Ontology (in AI)? In the simplest terms: ...

As powerful as large language models (LLMs) like GPT, LLaMA, and Mistral are, they’re still general-purpose. If you want to make them truly useful for your domain—whether it’s legal documents, financial analysis, or German tax law—you need to fine-tune them. And thanks to a technique called LoRA (Low-Rank Adaptation), you can now fine-tune LLMs with a fraction of the data, compute, and cost. 🔧 What is Fine-Tuning? Fine-tuning is the process of continuing the training of a pre-trained LLM on your own dataset so that it learns domain-specific patterns, vocabulary, tone, or tasks. ...

We hear the term knowledge graph everywhere now — from Google Search to enterprise AI to GenAI apps. But what exactly is a knowledge graph, and why is everyone suddenly obsessed with it? In this post, I’ll break down knowledge graphs in plain language: what they are, how they work, and how I use them in my own projects. 🧱 The Basics: What Is a Knowledge Graph? At its core, a knowledge graph is a network of real-world entities (people, places, things) and the relationships between them. It’s how machines can represent, understand, and reason about the world — kind of like a human brain, but for structured data. ...

We’ve all played with ChatGPT, Copilot, or Claude — typing in questions and marveling at their responses. But behind the scenes, there’s a powerful craft at play: prompt engineering. OpenAI and Anthropic both publish guidance on how best to prompt their models. It’s not just about “asking a question.” It’s about how you phrase it, structure it, and guide the model. Prompt engineering is the new programming skill — and it’s transforming how we interact with AI. ...

As large language models (LLMs) become central to search, productivity tools, education, and coding, evaluating them is no longer optional. You have to ask: Is this model reliable? Accurate? Safe? Biased? Smart enough for my task? But here’s the catch: LLMs are not deterministic functions. They generate free-form text, can be right in one sentence and wrong in the next — and vary wildly depending on the prompt. So how do we evaluate them meaningfully? ...

Large Language Models (LLMs) like GPT or LLaMA are great at generating text. But there’s a catch: They only know what they were trained on, and that knowledge is frozen at training time. So what happens when you ask them something from after their training cutoff? Or something super niche, like a policy from your internal HR docs? Enter RAG – Retrieval-Augmented Generation. A technique that combines LLMs with a search engine, enabling them to look up facts on the fly. ...

When people say “Transformers revolutionized NLP,” what they really mean is: Attention revolutionized NLP. From GPT and BERT to LLaMA and Claude, attention mechanisms are the beating heart of modern large language models. But what exactly is attention? Why is it so powerful? And how many types are there? Let’s dive in. 🧠 What is Attention? In the simplest sense, attention is a way for a model to focus on the most relevant parts of the input when generating output. ...