Reading
AXiA is an interactive web platform developed in 48 hours that uses local LLMs to convert NASA's exoplanet data into easy-to-understand educational descriptions, making complex astronomical data accessible to the general public.
Section 01
AXiA is an interactive web platform developed in 48 hours that uses local LLMs to convert NASA's exoplanet data into easy-to-understand educational descriptions, making complex astronomical data accessible to the general public.
Section 02
NASA's TESS (Transiting Exoplanet Survey Satellite) and Kepler missions have discovered over 17,000 exoplanets, accumulating massive amounts of astronomical observation data. For professional astronomers, this data is a valuable research resource, but for the general public, students, and even interdisciplinary researchers, it is like incomprehensible text—filled with technical parameters such as orbital period, transit duration, and stellar radius, lacking an intuitive way to understand and a cognitive bridge.
During the 48-hour hackathon of the 2025 NASA International Space Apps Challenge, the Mohsine Essat team built an interactive web platform called AXiA, whose core mission is simple: use the power of large language models to transform cold astronomical data into vivid, accurate, and educational natural language descriptions, allowing everyone to understand the stories of distant planets.
Section 03
AXiA's technical architecture is concise and elegant; it builds an end-to-end "data-text" generation pipeline:
Section 04
The platform integrates data from two of NASA's flagship missions:
In total, there are over 17,000 celestial entries, covering key physical parameters such as planet radius, orbital period, transit duration, and stellar mass.
Section 05
When a user selects an exoplanet, the system executes the following process:
Section 06
Section 07
AXiA's user interface design follows the principle of minimalism. Users only need to select an exoplanet from the dynamic dropdown menu, and the system immediately returns a customized description. These descriptions are not simple lists of data but narrative texts intelligently processed by LLMs—they will tell you how far the planet is from its host star, how many Earth days make up a "year" there, how many times its volume is that of Jupiter, and even speculate whether it might have an atmosphere.
This interactive approach completely changes the way the public accesses astronomical data. No longer needing to interpret obscure data tables or understand professional terminology, ordinary people can learn about worlds thousands of light-years away as if reading a story.
Section 08
AXiA's value goes far beyond a technical demonstration; it demonstrates the potential of AI to empower science communication in multiple dimensions:
Keep going with more reads from the same topic.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
Folkering OS is the world's first AI-native bare-metal operating system, entirely written in Rust no_std without relying on Linux, POSIX, or libc. It can generate commands from scratch, compile them into WASM, and run them in 10 seconds, achieving true self-evolution.
This project explores how to use Large Language Models (LLMs) to detect logical vulnerabilities in Ethereum smart contracts, especially business logic flaws that are difficult for traditional static analysis tools to capture, such as economic manipulation and execution order errors.
This article introduces an open-source project for building modern large language models from scratch. The project evolves from a GPT-2-style basic architecture to a Llama 2/3-style production-level implementation, covering complete tutorial implementations of key technologies such as RMSNorm, RoPE, SwiGLU, GQA, and MoE.