Generative Agents - Advances in Generative AI
Explore the cutting-edge world of generative agents in AI, examining their development, capabilities, and potential applications in modern technology and automation.
Part of Speech Tagging, Named Entity Recognition, and Hidden Markov Model
Master essential Natural Language Processing techniques including part-of-speech tagging, named entity recognition, and hidden Markov models for advanced text analysis.
Mixture of Transformers for Multi-modal Foundation Models
Explore Meta's Mixture-of-Transformers (MoT) architecture, a revolutionary approach to handling multi-modal AI tasks combining text, speech, images, and videos with enhanced efficiency and performance.
Reward-Guided Tree Search for Enhanced LLM Reasoning
Discover how reward-guided tree search enhances LLM reasoning capabilities through policy models, reward evaluation, and Monte Carlo algorithms for complex mathematical problem-solving.
AI Snake Oil: Understanding the Limitations and Potential of Predictive and Generative AI
Delve into a critical analysis of AI's dual nature - examining the ethical concerns of predictive algorithms while exploring the transformative potential of generative AI for knowledge work and society.
Introduction to AI - Understanding Core Technologies and Implementation Best Practices
Gain insights into AI fundamentals, from NLP and machine learning to ethical considerations, while exploring real-world applications, security practices, and implementation strategies.
The Frontiers of Modeling Atoms with AI
Explore cutting-edge AI applications in atomic modeling, focusing on drug discovery and climate change solutions, with insights into machine learning potentials and renewable fuel synthesis catalysts.
Is AI Sexist? Examining Gender Bias in Large Language Models
Explore how gender bias manifests in AI systems, particularly in Large Language Models, and learn practical steps to identify, understand, and address these biases in technology development.
From Retrieval to Real-Time Action: RAG, ReAct, and Flow Orchestrator in Building Smarter AI Bots
Explore cutting-edge AI techniques like RAG and ReAct, and learn how Microsoft's Flow Orchestrator enables dynamic, context-aware AI applications through a practical coding interviewer bot demonstration.
Simplifying Generative AI App Development - Standardization Matters
Explore best practices and open standards for generative AI development, focusing on LLM-based applications and RAG techniques while examining reference architectures and community initiatives.
LangChain Legends: Building LLM-Powered Applications
Master LangChain's framework for building powerful LLM applications through hands-on exploration of prompt templates, chains, agents, and memory, culminating in creating a practical RAG application.
A Deep Dive into Vector Search Technology and Tools
Explore vector search technology through practical demonstrations of ClickHouse, OpenSearch, and PGVector, learning how AI models convert text to vectors for enhanced contextual search capabilities.
10 Lessons from Building AI-Powered Features
Gain insights into practical lessons and strategies for integrating AI features into existing systems, from prompt engineering to responsible AI implementation, based on GitHub Copilot team experiences.
Applying Open Source Methods to Building and Training Large Language Models
Discover how to contribute domain knowledge to open source AI models through innovative workflows, enabling incremental improvements without full model retraining or forking. Learn practical approaches to collaborative AI development.
Enforcing Trustworthy AI Standards and Best Practices in Analytical Projects
Discover how to implement NIST's AI Risk Management Framework to build responsible and trustworthy AI systems, focusing on governance, mapping, measurement, and management best practices.
EfficientML.AI - Introduction to Efficient Machine Learning
Master efficient machine learning techniques and optimization strategies for deploying ML models in resource-constrained environments, focusing on practical implementation and performance tuning.
Multimodal AI: Understanding Large Language Models with Vision and Audio Capabilities
Explore three key approaches to expanding Language Models beyond text, enabling them to process visual and auditory information, with practical demonstrations using LLaMA 3.2.
Towards Infusing Auxiliary Knowledge for Distracted Driver Detection
Discover how auxiliary knowledge and scene graphs enhance distracted driver detection systems, improving accuracy by 13.64% through innovative integration of visual cues and driver pose information.
Custom, Targeted, and Neurosymbolic AI Models for Healthcare Applications
Explore the critical role of specialized AI models in healthcare, focusing on neurosymbolic approaches and compact solutions for improved medical applications and outcomes.
Fine-tuning AI Models for Healthcare Policy Analysis with AWS and Snorkel Flow
Master AWS and Snorkel Flow integration to enhance AI models through structured fine-tuning workflows, focusing on improving accuracy in analyzing health insurance policy documents and generating reliable responses.
The Elusive Role of High Dimensions in Modern Optimization and Generalization
Delve into the fascinating role of high-dimensionality in deep learning optimization, exploring how modern neural networks challenge traditional theoretical constraints and achieve unprecedented success.