News | simpleprog

machine learning Sep 11 The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement Modern AI systems can write code, reason through graduate-level science, and plan multi-step research workflows. But every improvement they undergo still requires humans to decide what to fix, build the resources to fix it, and ju...

machine learning Sep 11 Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport Diffusion models and flow-matching models generate images by progressively denoising a noisy sample over a series of timesteps. How that time is allocated across the denoising process, the schedule, has a direct impact on sample q...

machine learning Sep 11 Generative Late-Interaction Embeddings For Visual Document Retrieval Late-interaction retrieval has become the dominant paradigm for searching visual documents. Models like ColPali embed every image patch on a page as a separate vector and score queries against them using MaxSim, a per-token maximu...

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...