January 2026

Your genome has 3 billion base pairs. Less than 2% code for proteins. The other 98% isn’t “junk”—it’s the operating system. It contains the instructions controlling when and where genes activate. Most disease-associated variants hide in that 98%. But predicting what breaks when you change a single letter there is a massive challenge. The problem is context. Gene regulation operates over enormous distances. An enhancer can activate a gene from hundreds of thousands of base pairs away. If […]

Ver mais

Originally in 2019, GPT-2 was trained by OpenAI on 32 TPU v3 chips for 168 hours (7 days), with $8/hour/TPUv3 back then, for a total cost of approx. $43K. It achieves 0.256525 CORE score, which is an ensemble metric introduced in the DCLM paper over 22 evaluations like ARC/MMLU/etc. As of the last few improvements merged into nanochat (many of them originating in modded-nanogpt repo), I can now reach a higher CORE score in 3.04 hours (~$73) on […]

Ver mais

Deep learning has revolutionized medical image analysis, playing a vital role in modern clinical applications. However, the deployment of large-scale models in real-world clinical settings remains challenging due to high computational costs, latency constraints, and patient data privacy concerns associated with cloud-based processing. To address these bottlenecks, this review provides a comprehensive synthesis of efficient and lightweight deep learning architectures specifically tailored for the medical domain. We categorize the landscape of modern efficient models into three primary streams: […]

Ver mais

PyGALAX is a Python package for geospatial analysis that integrates automated machine learning (AutoML) and explainable artificial intelligence (XAI) techniques to analyze spatial heterogeneity in both regression and classification tasks. It automatically selects and optimizes machine learning models for different geographic locations and contexts while maintaining interpretability through SHAP (SHapley Additive exPlanations) analysis. PyGALAX builds upon and improves the GALAX framework (Geospatial Analysis Leveraging AutoML and eXplainable AI), which has proven to outperform traditional geographically weighted regression (GWR) […]

Ver mais

Hi guys, recently I got a project on using machine learning to recognize rice lodging in rice fields. So, my first steps are to try to label the images into rice fields and non-rice fields area so that later I could develop an algorithm to ignore the non-rice fields area and then recognize the rice lodging area. However, I am not sure which tool I should use. I have seen people recommend using GIMP, CVAT and labelme. But […]

Ver mais

When Renee Good and Alex Pretti were murdered, and I saw the incredible courage of people in Minneapolis in the face of state brutality, I had to find some way to show that tech workers stand with Minnesota, even if our leaders don’t. I signed the ICEout petition, and I’d encourage you to do the same. I’ve also been talking to the press about why I signed it, and on the Wired Uncanny Valley podcast Kate Drummond asked […]

Ver mais

The advent of the web has led to a paradigm shift in the financial relations, with the real-time dissemination of news, social discourse, and financial filings contributing significantly to the reshaping of financial forecasting. The existing methods rely on establishing relations a priori, i.e. predefining graphs to capture inter-stock relationships. However, the stock-related web signals are characterised by high levels of noise, asynchrony, and challenging to obtain, resulting in poor generalisability and non-alignment between the predefined graphs and […]

Ver mais

I’m working on a project that involves a DQN trying to optimize some experiments that I have basically gamified to try to reward exploration/diversity of trajectories. I understand the fundamentals underlying DQN but haven’t worked extensively with them prior to this project so I don’t have much intuition built up on it yet. I’ve seen varying ideas regarding training params– I’m training for 200k steps (each step the agent makes 4 actions), but I’m not sure how I […]

Ver mais

We study solution learning for heat-based equations in self-similar variables (SSV). We develop an SSV training framework compatible with standard neural-operator training. We instantiate this framework on the two-dimensional incompressible Navier-Stokes equations and the one-dimensional viscous Burgers equation, and perform controlled comparisons between models trained in physical coordinates and in the corresponding self-similar coordinates using two simple fully connected architectures (standard multilayer perceptrons and a factorized fully connected network). Across both systems and both architectures, SSV-trained networks consistently […]

Ver mais

Hi everyone, Michael Reilly here. As March draws to a close—and we wrap up the month with an investigation into how NYC’s AI-powered bot tells people to break the law—I’ve been asking around the newsroom to find out what else has captured my colleagues’ interest and fascination over the last month. Below you’ll find an eclectic mix of the things that we read, play, listen to, and otherwise feed our brains with when we’re not heads down doing […]

Ver mais