Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA
[New paper] https://arxiv.org/abs/2607.21861
Software Engineering Has Expanded: Choosing Between Rules, Prompts, Chains, and Agents
Software engineering has expanded to solve new kinds of problems that weren’t practical before. There are 4 ways to solve problems , depending on how certain we are about the path …
The Platform For The Universal Personal Assistant
The quest to build the universal personal assistant (UPA) has been reignited, with both OpenAI and Google going head to head. But what would the ultimate personal assistant look li…
Evolution of Media: From Ancient Communications to AI-Generated Content
Ancient Media Sharing stories and messages with an audience has been a fundamental human need since ancient times. From smoke signals and hieroglyphs to theatre acts and folklore s…
MemGPT: Enhancing LLM Capabilities Through Operating System Principles
Large Language Models (LLMs) have transformed artificial intelligence, leading to significant advancements in conversational AI and applications. However, these models face limitat…
Simplifying Language-Image Pre-Training with Sigmoid Loss
Introduction to Language-Image Pre-Training Language-Image Pre-Training (LIP) has become a popular approach to obtain robust visual and textual representations. It involves alignin…
ColPali: A Breakthrough in Efficient Document Retrieval
Introduction to ColPali ColPali is a novel document retrieval model that significantly enhances the efficiency and accuracy of matching user queries to relevant documents. It lever…
Introduction To Building LLM Applications
I've put together this presentation to help anyone with a technical background to build their own LLM powered applications. The topic is quite broad but it covers all the basic mov…
Kaggle Docs QA With Gemma - Data Collection + Dataset Generation + Fine Tuning + RAG + ColBERT Re-Ranker + Evaluation
Sharing my my notebook for the Google AI Assistants For Data Task With Gemma competition. The notebook (link at the end) covers the basic building blocks to adapt LLMs for your own…
VQA and Image Chunking for MLLMs (GPT-4V and Gemini)
MLLMs (Multi Modal Large Language Models) such as GPT-4V and Gemini are able to ingest data in multiple modalities such as: text, video, sound and images. Personally, one of the mo…
The Generative Internet
Generative AI is opening the doors to new products. It's great to witness in real time how the Internet is evolving and to imagine what it might become in the coming years. Search,…
🚧 Constraining AI agents increases reliability
Working with LLMs is shifting from human-machine interactions to human-machine and machine-machine interactions. This allows LLMs to do ever more complex tasks. This new interactiv…
Document Chunking for RAG (Retrieval Augmented Generation)
LLMs have a limited input they can generate and output. In retrieval augmented generation (RAG) applications, a set of documents is first retrieved and added to the input alongside…
📖 Can LLMs find knowledge gaps in the Internet?
🚀 Excited to share new work on “ Harnessing Retrieval-Augmented Generation (RAG) for Uncovering Knowledge Gaps “. In this paper, I simulate how users search the Internet but instea…
How can Adept's FUYU be used for UI Navigation?
Adept's mission to enable computers to interact with UIs will enhance our productivity and save time. I have been eagerly awaiting their ACT-1 model for quite some time. However, w…