Loren Lugosch
1.2K posts
@lorenlugosch
Machine learning @ ; audio & language; Freigeisterei und Vielgeisterei; "at once a man of business and a man of rhyme"
Excited to share our new work — SimpleSD: Embarrassingly Simple Self-Distillation! 🎉 Huge thanks to my incredible co-authors for making this happen! 📄 Paper: arxiv.org/abs/2604.01193 💻 Code: github.com/apple/ml-ssd 🤗 Models: huggingface.co/collections/ap…
1/6 The "Self-Improvement" Paradox Can an LLM get smarter using only its own raw, unverified outputs? No verifiers. No teachers. No RL. We found the answer is an emphatic YES. Introducing SimpleSD: Embarrassingly Simple Self-Distillation. By simply sampling solutions from a model with specific temperature and truncation settings and then fine tuning the model on those exact samples, Qwen3-30B jumped from 42.4% to 55.3% (30% improvement) on LiveCodeBench v6 just by training on its own samples! 🚀 The gain is universal across different model sizes (4B, 8B, 30B) and model families (Llama, Qwen). The harder the problem is, the larger the gain. 📈 Kudos to my amazing colleagues @onloglogn, @richard_baihe, @UnderGroundJeg, Navdeep Jaitly, @trebolloc. Check out the paper and code below! 👇 paper: arxiv.org/abs/2604.01193 code: github.com/apple/ml-ssd HF models: huggingface.co/collections/ap…
Pokemon Go players unknowingly helped train delivery robots after generating over 30 billion real-world scans through the game That data is now being used to help autonomous robots navigate city streets
I want to make /init more useful- what do you think it should do to help setup Claude Code in a repo?
