Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation Paper • 2602.17316 • Published Feb 19 • 1
Zagreus - Nesso fine tuned Collection The collection contains three bilingual English/Italian SLMs post-trained on Zagreus-0.4B-ita: instruct, agentic, and a fully open-source • 3 items • Updated 21 days ago • 3
Zagreus 0.4B Collection The Zagreus-0.4B collection contains four bilingual English + Romance language foundational SLMs (~400M parameters) trained from scratch • 4 items • Updated 21 days ago • 6
view article Article Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries +7 15 days ago • 78
Running Featured 69 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems 📝 69 Who needs 1T parameters? Olympiad proofs with a 4B model
view article Article From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output Feb 7 • 22