News | simpleprog

machine learning Sep 11 Thinking with Looped Flows The ability to solve harder problems by spending more time on computation is one of the most fundamental ideas in both human cognition and computer science. Autoregressive language models achieve this by writing out their reasonin...

machine learning Sep 10 Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization World models are supposed to learn dynamics, not just predict the next frame. But does a model that predicts the next latent state accurately over a single step actually understand physics when that prediction is composed over doz...

machine learning Sep 07 Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation How Amazon Trains a 15M-Parameter Model to Replace LLM Calls for Product Upgrade Recommendations E-commerce platforms need to recommend better products to customers, not just similar ones. A shopper buying a basic moisturizer shou...

machine learning Sep 06 Revise is the Figma of machine learning Machine learning workflows are slow, fragmented, and often require sending sensitive data to cloud services. Revise, a new no-code platform, tries to solve all three problems at once by providing a guided interface for cleaning da...

machine learning Sep 05 The Roadmap of Mathematics for Machine Learning Understanding the mathematics behind machine learning algorithms gives you a significant advantage when working on real problems. Most of this knowledge is hidden behind layers of advanced mathematics, but with proper foundations,...