Discover AI Courses

Sonnet 3.7 "THINK" Tool: More Than a Scratchpad

Explore Anthropic's new "THINK" Tool for Claude Sonnet 3.7, understanding its performance benefits, use cases, and how it goes beyond being a simple scratchpad for more reliable AI reasoning and problem-solving.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Reasoning LLM Overthinking - Easy Solution

Discover a simple, free solution to improve distilled reasoning LLMs that tend to overfit and underperform, based on new research findings about enhancing reasoning capabilities with less overthinking.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Knowledge Graphs with AI Agents - From CRYSTAL to Self-Organizing Knowledge Networks

Explore how AI agents build and utilize knowledge graphs to create coherent, self-organizing networks for enhanced reasoning and information processing.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

GraphRAG vs In-Context Learning: Comparative Analysis and Performance Differences

Explore the differences between GraphRAG and In-Context Learning systems, comparing their performance, implementation strategies, and optimal use cases for AI reasoning tasks.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Training and Evaluating Tiny Language Models for Edge Device Agents

Explore the development and scalability of TINY Language Models for AI agents on edge devices, focusing on training methodologies and practical implementations.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

Optimizing Small Language Models for In-Vehicle Function Calling

Discover groundbreaking research on optimizing small language models for in-vehicle systems, focusing on efficient function-calling implementations by Mercedes-Benz.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Multi-Agent AI Systems: Simple Implementation with Smolagents Framework

Learn to build multi AI-agent systems using the smolagents framework, featuring simplified code implementation and decentralized AI intelligence for solving complex problems.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

Introduction to SmolAgents - HuggingFace's Simple AI Agent Framework

Discover HuggingFace's Smolagents framework, a straightforward approach to building AI agents with comprehensive documentation, tutorials, and seamless integration with HuggingFace models.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Byte Latent Transformer: Token-Free Architecture Using Entropy-Based Byte Prediction

Dive into the innovative Byte Latent Transformer architecture, exploring entropy-based byte prediction, causal local attention mechanisms, and cross-attention for latent patches in tokenizer-free models.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Dirichlet Energy Minimization Explains In-Context Learning

Explore groundbreaking Harvard research on how Dirichlet Energy Minimization explains in-context learning in LLMs, optimizing RAG systems and transformer learning without expensive fine-tuning.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Better In-Context Learning and RAG System Optimization

Dive into cutting-edge research on optimizing Large Language Models through improved In-Context Learning and RAG systems, without expensive fine-tuning or pre-training procedures.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Two-Phase Pretraining - Enhancing LLM Accuracy and Scalability

Discover cutting-edge techniques for enhancing Large Language Model training through a two-phase approach, focusing on core functionalities to improve accuracy and scalability.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Code Chain of Thought with Self-Evolution LLM: rStar-Math Mathematical Reasoning Framework

Delve into Microsoft's rStar-Math framework, exploring how small language models can achieve advanced mathematical reasoning through self-evolution and Monte Carlo Tree Search techniques.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

Beyond RAG: Continual Learning of Large Language Models with InCA

Discover how InCA enables continuous learning in LLMs through innovative in-context learning and external modules, offering an alternative to traditional RAG and fine-tuning approaches.

• YouTube
• 40 minutes
• Self-Paced
• Free Video

Building Adaptive Multi-Agent AI Systems: From Theory to Implementation

Explore adaptive multi-agent AI systems through reinforcement learning, examining how agents navigate dynamic physical and social environments while developing cooperative strategies and decision-making capabilities.

• YouTube
• 24 minutes
• Self-Paced
• Free Video