Jorge Martinez Santiago

gLSTM extends xLSTM to a graph neural network architecture: https://lnkd.in/da3at-Y9 "gLSTM mitigates sensitivity over-squashing and capacity over-squashing." "gLSTM achieves comfortably state of the art results on the Diameter and Eccentricity Graph Property Prediction tasks, and very strong performance on SSSP"

267

5 comentarios

 🛠️🧰⚙️🔧 TOOLS FOR TRUSTWORTHY AI  🛠️🧰⚙️🔧 🥐 Croissant by MLCommons: An open standard to describe AI datasets clearly and consistently Understanding the structure, context, and purpose of AI datasets is critical for transparency, reproducibility, and responsible innovation. That’s where 🥐 Croissant comes in — a new open standard developed by MLCommons, a leading non-profit engineering the foundation for open and trustworthy AI. 🥐 Croissant makes it easier to describe and share datasets in a machine-readable format, supporting better data documentation, discovery, and reuse. Its key features: 🔹 Uses JSON-LD for compatibility with modern data ecosystems 🔹 Provides dataset metadata on structure, provenance, licensing, and more 🔹 Designed to support data cards and model cards 🔹 Enables integration with common AI pipelines and tooling Croissant is part of the OECD.AI Catalogue of Tools & Metrics, a global resource to support trustworthy AI by helping developers, researchers, and policymakers find open tools that align with the OECD Principles for Trustworthy AI. Croissant is an important step toward solving one of AI’s most persistent problems: opaque and undocumented training data. What are your thoughts on tools like this? Could they become part of mainstream AI governance frameworks? 👇 Find a link below in the comments to 🥐 Croissant's page in the OECD Catalogue of Tools & Metrics for Trustworhty AI👇

285

13 comentarios

Now on GitHub ⚙️ A new pull request adds a diffusion-based trajectory planner as part of a modular end-to-end approach in #Autoware, where machine learning supports both prediction and planning. This enables more natural driving behavior in complex scenarios 🚗💻 See details🔗 https://hubs.li/Q03G1MJP0 #EndtoEnd #AI #OpenSource #TIERIV

156

🚀 Machine Learning Time Complexity: A Guide for MLOps Engineers (Optimize your models before they drain your compute budget) ✅ Decision Trees & Random Forests Efficient for many tasks, but deeper trees and large datasets can degrade performance. ✅ Neural Networks Highly powerful, but require heavy computation during training and inference. ✅ K-Nearest Neighbors (KNN) Training is fast, but inference slows as dataset size grows due to distance calculations. ✅ K-Means Clustering Great for unsupervised learning, but complexity increases with more clusters and iterations. ➡️ Why it matters for MLOps: Understanding time complexity helps reduce inference latency, optimize training pipelines, and manage compute resources effectively. Use this as your cheat sheet to deploy smarter, faster models. ⚡ 🎓 Learn Machine Learning & MLOps – Free Courses 🔗 Generative AI for Data Scientists → https://lnkd.in/dRYW2t26 🔗 IBM Data Science → https://lnkd.in/dhtTe9i9 🔗 SQL Basics for Data Science → https://lnkd.in/d6-JjKw7 🔗 Machine Learning Engineer – Career Academy → https://lnkd.in/dVGrGzBe 🔗 Top Python Machine Learning Libraries → https://lnkd.in/dTdWqpf5 📌 Save this visual 🔁 Repost to support other data professionals 🌐 More at: https://lnkd.in/dJw7mE-x ✍️ Image Credit: DataInterview.com #MachineLearning #MLOps #AI #DataScience #Python #FreeCourses #DeepLearning #ProgrammingValley #ModelOptimization #100DaysOfML #TechCareers

261

2 comentarios

How complex is your AI model, really? A new paper in Nature Machine Intelligence by IBM researcher Takuya Ito and team introduces a novel approach to quantifying algorithmic generalization in AI systems using computational complexity theory: https://ibm.co/6043BHl0T By testing models on circuit problems of varying difficulty, the team developed a standardized framework to benchmark computational complexity—providing deeper insights into model reasoning and guiding future architectural innovations. This work lays the foundation for more transparent, efficient, and trustworthy AI.

277

Automate detection of unreliable LLM outputs by combining MLflow tracing with Cleanlab’s Trustworthy Language Models (TLM). 🚀 This blog post covers: ✅ Setting up MLflow to capture complete LLM interactions, including system prompts. ✅ Retrieving traces and efficiently batch-evaluating them with TLM to get trustworthiness scores and explanations—without ground truth labels. ✅ Tagging each MLflow trace with its trust score and explanation for ongoing review. ✅ Using MLflow Evaluation with a custom TLM metric to systematically compare model outputs. For the full guide and code samples, read more ➡️ https://lnkd.in/eHNWQrrK cc Chris Mauck, Data Scientist at Cleanlab #opensource #llm #oss #mlflow #cleanlab

59

1 comentario

Starting today, Claude Sonnet 4 supports 1 million tokens of context on the Anthropic API—5x more than before. This enables developers to process over 75,000 lines of code or dozens of research papers in a single request, ideal for data-intensive uses like long-running agents. Long context support for Sonnet 4 is now in public beta, starting with API users on Tier 4 and custom rate limits. Broader availability on our API will be rolling out over the coming weeks. It’s also available in Amazon Bedrock, and is coming soon to Google Cloud's Vertex AI. Learn more about Sonnet 4 and the 1M context window: https://lnkd.in/e-tfCYBg

6640

434 comentarios