Discover AI Courses

Unsupervised In-Context Learning Plus: From Few-Shot to Many-Shot Learning in Large Language Models

Explore advanced In-Context Learning techniques for Large Language Models, from few-shot to many-shot approaches, focusing on unsupervised learning and autonomous capabilities with 1M token context.

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

RecurrentGemma: Moving Past Transformers with Griffin Architecture for Long Context Length

Explore Google's RecurrentGemma-2B architecture, featuring Griffin's innovative approach to language modeling that surpasses traditional transformers with enhanced efficiency and long-context processing capabilities.

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

TransformerFAM and BSWA: Understanding Feedback Attention Memory and Block Sliding Window Attention

Dive into Google's revolutionary TransformerFAM architecture, exploring how feedback attention mechanisms and working memory enhance AI's ability to process indefinite sequence lengths with improved efficiency and context awareness.

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

INFINI Attention: Efficient Infinite Context Transformers with 1 Million Token Context Length

Explore Google's Infini-attention transformer mechanism, featuring compressive memory integration for handling million-token sequences and efficient long-term information processing.

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

Ring Attention and Blockwise Transformers for Extended Context Length in Language Models

Dive into the technical mechanics of Ring Attention, exploring how it achieves million-token context lengths in large language models through blockwise parallel transformers and efficient implementation.

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

On-Device LLMs with Functional Token Fine-Tuning - Octopus v2 Implementation

Explore cutting-edge developments in on-device LLMs, focusing on functional token fine-tuning and Octopus v2 technology for enhanced efficiency and performance on edge devices.

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

ORPO: A New Preference-Aligned Training Method for Large Language Models

Explore a groundbreaking reference model-free optimization algorithm for LLM training, comparing ORPO's performance with Llama 2 and Mistral 7B through theoretical physics perspectives.

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

Symmetry Breaking in AI Diffusion Models - Dynamical Regimes and Optimization

Explore groundbreaking research on symmetry breaking patterns in AI diffusion models and their impact on optimization and transformation processes.

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

Diffusion Transformer and Rectified Flow in Stable Diffusion 3

Dive into the mechanics of Diffusion Transformers, exploring noise distribution, latent space dimensionality, and the innovative Rectified Flow technology powering next-gen AI image generation.

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

Writing the Perfect AI Prompt - A Guide to Cross-Platform Prompt Engineering

Master the art of crafting effective prompts for LLMs like GPT-4 and Claude 3, exploring formatting techniques, cross-model compatibility, and best practices for optimal AI interactions.

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

Protecting RAG Systems from Generative AI Worms - AI Cybersecurity Threats and Countermeasures

Explore the emerging threat of GenAI Worms, their impact on RAG and LLM systems, and learn essential cybersecurity countermeasures to protect AI infrastructure.

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

Generative Interactive Environments (GENIE) - Creating Synthetic Video Game Worlds

Explore GENIE AI's groundbreaking technology for generating interactive video environments, featuring advanced neural networks and transformers for synthetic world creation.

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

Simple Ideas to Improve Your Retrieval-Augmented Generation Systems

Discover practical strategies to enhance RAG systems using insights from Stanford and Google research, focusing on GNN implementation and improved query-text mapping techniques.

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

DSPy Combined with Graph Optimizer in PyG - Multi-Hop RAG Implementation

Explore DSPyG's innovative approach to multi-hop RAG implementation, combining DSPy with graph optimization for enhanced AI research capabilities using minimal computational resources.

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

DSPy for In-Context Learning and RAG Classification - Code Explained

Explore state-of-the-art extreme multi-label classification using DSPy's Infer-Retrieve-Rank program, combining frozen retrieval with in-context learning for optimal results.

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