Load, Transform & Publish at Scale: Introducing the Hugging Face Provider for Apache Airflow
AINovice2005
• NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Measuring a prompt-complexity router against local LLM judges: an open, replayable bench
scombat
• HyperAPI: one API for every enterprise document, plus ten open benchmarks to test it
nchhaya
• aemon: teaching a 3B model to investigate a strategy question, with AgentTune and AuditKIT
HatemSaadallah
• TikTok Video Size, Measured With ffprobe: A Batch Checker for UGC Ads
Jacob123222
• CiberIA Expected Cognitive Profile Fast v1.0: laya
gcjordi
• Yang-Mills, OpenAI proof, and the mass gap problem
dlouapre
• • 11Which Weather Model Is Most Accurate? We Score Them Every Day, in the Open
FINAL-Bench
• • 7Fantasy Football Punishment Video: Last Place Sings the Tiny Desk Meme
akagease
• Copying without attention: Fourier readout of a fixed-size wave memory
datatab
• Asked for anatomy, it returned a drug: two new small OpenMed models for drugs and anatomy
OpenMed
• Declining Consensus Use in a Seven-Machine LLM Agent Fleet
TonyDzi
• Isoglot: Tiny Aya's safety gap in African languages is a comprehension gap
NFTKING
• Is Tiny Desk AI Free? What the Free Preview Shows Before You Pay
rapvideo
• • 1TiHon-TTS: Vietnamese text-to-speech in 100K parameters, small enough for a microcontroller
ngocthien
• • 1High-Stakes Embodied Agents: Two Full Post-Training Loops with Honest Safety Numbers on Disaster Response Scenario
sanggusti
• Inkling 2 Small Uncensored: refusals removed, hours after release
OpenUncensored
• Relational AI is the future. In fact, it's really British sci-fi comedy.
PeaceBitCreativeStudio
• On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery
litert-community
• • 8How to Test Your MCP Server with Coding Agents
phranzia
•