Machine Learning
273 articles in this category (Page 11 of 12)
Build and Train Advanced Architectures with Residual Connections, Self-Attention, and Adaptive Optimization Using JAX, Flax, and Optax
A JAX-based tutorial implements self-attention and residual blocks, achieving 92% accuracy on synthetic data with adaptive optimization.
Prior Labs Launches TabPFN-2.5: Scaling Tabular Foundation Models for Enhanced Performance and Efficiency
Prior Labs introduces TabPFN-2.5, a major update to its tabular foundation model, enabling handling of 50,000 samples and 2,000 features with no training required, while outperforming traditional models on benchmarks.
Multi-Agent System for Integrated Multi-Omics Data Analysis with Pathway Reasoning
A tutorial on building a multi-agent system to analyze transcriptomic, proteomic, and metabolomic data for biological insights using pathway reasoning and drug repurposing.
Moonshot AI Introduces Kimi K2 Thinking: A Breakthrough in Long-Horizon Reasoning and Tool Use
Moonshot AI releases Kimi K2 Thinking, an open-source thinking model capable of executing 200–300 sequential tool calls without human intervention, optimized for long-horizon reasoning and agentic tasks.
Google AI Introduces Consistency Training for Safer Language Models Under Sycophantic and Jailbreak Style Prompts
Google AI introduces Consistency Training (Bias Augmented Consistency Training and Activation Consistency Training) to enhance language models' safety against sycophantic and jailbreak prompts while preserving their capabilities.
Generalist AI Introduces GEN-θ: A New Era of Embodied Foundation Models for Robotics
Generalist AI's GEN-θ is a groundbreaking embodied foundation model trained on real-world physical interaction data, enabling scalable robotics through Harmonic Reasoning and large-scale multimodal pre-training.
How Can We Build Scalable and Reproducible Machine Learning Experiment Pipelines Using Meta Research Hydra?
This article explains how to use Meta's Hydra framework to create scalable and reproducible ML experiments through structured configurations, overrides, and multirun simulations.
How AI Models Are Trained: Ethical Concerns and the Rise of Responsible AI Development
This article explores the training process of AI models, ethical challenges in data collection, and the global push for responsible AI development to ensure fairness, transparency, and accountability.
Anthropic's Research Demonstrates Claude's Introspective Awareness Through Concept Injection in Controlled Layers
Anthropic's study reveals that Claude models can detect injected concepts via internal activations, offering causal evidence of introspection. The research highlights controlled success rates and implications for LLM transparency.
Predictive Analytics and Auto-Remediation in AIOps: Transforming DevOps with Machine Learning
Explore how predictive analytics and auto-remediation in AIOps enable proactive system management, reducing downtime and improving DevOps efficiency through machine learning.
Meta's AI-Driven Approach to Standardizing and Reducing Carbon Emissions in IT Hardware Supply Chains
Meta leverages AI to enhance Scope 3 emissions reporting by classifying hardware components and inferring missing carbon footprint data, contributing to global sustainability efforts through open-source collaboration.
7 Advanced Feature Engineering Tricks for Text Data Using LLM Embeddings
Explore seven advanced techniques to enhance text-based machine learning models by combining LLM-generated embeddings with traditional features, improving accuracy in tasks like sentiment analysis and clustering.
Microsoft Releases Agent Lightning: A Reinforcement Learning Framework for Optimizing AI Agents
Microsoft introduces Agent Lightning, an open-source framework that enables reinforcement learning (RL)-based training of large language models (LLMs) for AI agents without requiring changes to existing agent stacks.