The drug design engine we’re building at @IsomorphicLabs is extending the SOTA further across key benchmarks, showing huge progress in accuracy and capabilities critical for in-silico drug discovery. Incredible work from @maxjaderberg and the entire team at Isomorphic Labs!
MACHINE LEARNING
-
Open-source ML Systems Textbook — Principles & Practices
By
–
#MachineLearning Systems — The Principles & Practices of Engineering Artificially Intelligent Systems: http://
mlsysbook.ai by @profvjreddi [Updated 2000+ pages PDF] Open-source textbook on how to design and implement #AI systems effectively.
————
#ML #MLOps #DataScience -
Agentic Design Patterns: Guide to Building Intelligent Systems
By
–
"Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems" Read the Online eBook from Google at https://
docs.google.com/document/d/1rs
aK53T3Lg5KoGwvf8ukOUvbELRtH-V0LnOIFDxBryE/mobilebasic?pli=1#heading=h.pxcur8v2qagu
… Buy hardcopy version at http://
amzn.to/3IyOrPx -
Practical Guide: Building AI Agents with LLMs, RAG, and Knowledge Graphs
By
–
"Building AI Agents with LLMs, RAG, and Knowledge Graphs — A practical guide to autonomous and modern AI agents" See it at http://
amzn.to/4622k2h via @PacktDataML -
Integration transforms AI potential into testable operational systems
By
–
There is something tangible in seeing these pieces come together, because integration turns potential into systems that can actually be tested and stressed. When different technologies start operating as one, progress feels less speculative and more grounded, so the timeline
-
RF-DETR and NAS: One Model for Infinite Possibilities
By
–
One Model, Infinite Possibilities: RF-DETR & NAS
— Satya Mallick (@LearnOpenCV) 10 février 2026
Ever wondered how AI models balance speed and accuracy without constant retraining? 🧠 Deep dive into how RF-DETR uses Neural Architecture Search (NAS) and weight sharing to create a "super-model." By training once and adjusting… pic.twitter.com/yLnmTAdWUZOne Model, Infinite Possibilities: RF-DETR & NAS Ever wondered how AI models balance speed and accuracy without constant retraining? Deep dive into how RF-DETR uses Neural Architecture Search (NAS) and weight sharing to create a "super-model." By training once and adjusting
-
Unitree G1 Robot Struggles with Snow: Early Progress in Robotics
By
–
Watching the Unitree G1 struggle with snow is oddly reassuring and exciting. Today it slips, hesitates, and fights the basics.
Tomorrow, it won’t get tired, won’t complain, and won’t miss a spot. This is what early progress looks like: awkward before it’s invisible.
Physical -
Old-School Interpretability Methods for Large Language Models
By
–
Old-School Interpretability for LLMs https://
buff.ly/VC4ScSD
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Understanding Learning Processes Beyond Single Environment Solutions
By
–
If your problem can be solved that way, great! It is a Tool That Works. However, the challenges around single environment, limited sample regimes should still call into question our level of understanding of the basic learning process, and deeper understanding there is plausibly