Reliable PDF to Latex!

This talk demonstrates a pipeline converting complex PDFs with tables and notation into a new LaTeX project, preserving content parity.

LLM Vercel Next TypeScript Postgres

Overview

A pipeline that can take a long PDF that includes tables and complex notation and build it as a new Latex project with content parity.

PDF -> Code

Links

https://uncompiler.com
Uncompiler reconstructs flat PDFs into structured, compiling LaTeX projects.

Tech stack

LLM

Large Language Models (LLMs) are deep learning models, built on the Transformer architecture, that process and generate human-quality text and code at scale.

LLMs are a class of foundation models: massive, pre-trained neural networks (often with billions to trillions of parameters) that leverage the self-attention mechanism of the Transformer architecture (introduced in 2017) to predict the next token in a sequence. Trained on vast datasets (e.g., Common Crawl's 50 billion+ web pages), these models—like GPT-4, Gemini, and Claude—acquire predictive power over syntax and semantics. They function as general-purpose sequence models, enabling critical applications such as complex content generation, language translation, and automated code completion (e.g., GitHub Copilot). Their core value: generalizing across diverse tasks with minimal task-specific fine-tuning.

https://en.wikipedia.org/wiki/Large_language_model

View projects
Vercel

Vercel is the Frontend Cloud: a unified platform for building, deploying, and scaling modern web applications, including Next.js, with performance-focused global infrastructure.

Vercel delivers a frictionless developer experience for the modern web, focusing on the 'Develop, Preview, Ship' workflow. As the creator and maintainer of the Next.js framework, Vercel offers first-class support for full-stack React applications, alongside other popular frameworks like SvelteKit and Nuxt. Its core value is instant, Git-based deployment (e.g., automatic preview environments for every pull request) and automatic scaling via serverless functions (Edge Functions) and a global Content Delivery Network (CDN). This infrastructure ensures high performance, low latency, and zero-configuration scaling for applications used by companies like Apple and IBM.

https://vercel.com

View projects
Next

Next.js is the full-stack React framework: it delivers high-performance web applications via hybrid rendering and powerful, Rust-based tooling.

This is the React Framework for production: Next.js enables you to build full-stack web applications with zero configuration and maximum efficiency. It supports a hybrid rendering approach (Server-Side Rendering, Static Site Generation, and Incremental Static Regeneration) for optimal speed and SEO performance. Key features include React Server Components, Server Actions for running server code directly, and the App Router for advanced routing and nested layouts. Developed by Vercel, it leverages Rust-based tools like Turbopack and the Speedy Web Compiler for the fastest possible builds and a superior developer experience.

https://nextjs.org/

View projects
TypeScript

TypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.

TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).

https://www.typescriptlang.org/

View projects
Postgres

Postgres is the world's most advanced open-source object-relational database, engineered for enterprise-level reliability and data integrity.

PostgreSQL (Postgres) is a powerful, open-source object-relational database system: it extends the SQL standard and handles complex data workloads with proven architecture. Its origins trace back to 1986 at UC Berkeley. The platform is fully ACID-compliant and uses Multi-Version Concurrency Control (MVCC) to manage high transaction rates with minimal locking. Key features include robust extensibility, allowing users to define custom data types and functions, plus a vast ecosystem of add-ons like the PostGIS geospatial extender. This focus on reliability and feature depth makes it the top choice for critical applications across all major operating systems.

https://www.postgresql.org/

View projects

Reliable PDF to Latex!

Related talks