5+ hour, 17+ min ago   (1666+ words) Why is subliminal learning (pattern transmission through noise) possible? Why does training on synthetic data lead to degradation, even when the data appears to be of high quality? In this article, I propose looking at training architecture from a different…...

1+ week, 4+ day ago   (613+ words) As we wrap up another year, it's time to look back at what our department has accomplished. 2025 brought us 42 published papers spanning fundamental ML theory, applied AI systems, and cutting-edge optimization methods'from transformer Hessians and generative models to hallucination detection…...

2+ week, 12+ hour ago   (477+ words) Ollama has become the standard for running Large Language Models (LLMs) locally. In this tutorial, I want to show you the most important things you should know about Ollama. Watch on YouTube:Ollama Full Tutorial Windows: download the.exeinstaller and…...