Unify Courses

Unify: Routing to Minimize Cost - Demo 01

Optimize LLM query costs through dynamic routing based on input and output pricing, balancing performance and budget constraints.

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

Accelerating MMPretrain Models with JAX - Demo 16

Accelerate MMPreTrain models by converting to JAX for faster inference. Learn efficient development, instant sharing, and optimal deployment of ML solutions.

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

Ivy: Quickstart and Introduction to Features - Demo 01

Get up to speed with Ivy's features and capabilities for efficient machine learning development, instant sharing, and optimal deployment.

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

The Fragmented ML Stack and How to Fix It

Explore the fragmented ML stack, understand Ivy's role in unification, and see demonstrations of function, library, and model transpilation.

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

Deep Dive: Ivy Frontend Tests - Tutorial 17

Explore frontend testing in Ivy, covering key techniques and best practices for ensuring robust web applications.

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

Building an AI App for Marking Student Math Questions - Part 26

Enhance your knowledge of AI app development for marking math questions, focusing on agent optimization with structured output and evaluation.

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

Building an AI App - Part 4: Uploading Test Sets and Partitions

Dive into building an AI app for marking math questions, learning how to upload test sets and partitions into the Unify platform.

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

Building an AI App for Marking Student Math Questions - Part 7

Dive into building an AI app for marking math questions, focusing on the first iteration of agent optimization flywheel implementation.

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

Building an AI App for Marking Student Math Questions - Part 18

Enhance your knowledge of AI app development for marking math questions with agent optimization, mark type descriptions, and reasoning mark guidelines.

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

Building an AI App: Marking Student Math Questions - Part 34

Explore agent traces in iteration 9 of an AI app for marking math questions, verifying correct system message formatting.

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

The Janus Interface - Privacy Risks in Fine-Tuning Large Language Models

Explore how fine-tuning in large language models can amplify privacy risks, focusing on the novel Janus attack that recovers forgotten personal information from pre-training data.

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

Knowledge Circuits in Pretrained Transformers Explained

Explore knowledge circuits in pretrained transformers, uncovering computational mechanisms behind language models' articulation of specific knowledge. Gain insights into AI's inner workings.

• YouTube
• 1 hour
• Self-Paced
• Free Video

Hierarchical Prompting Taxonomy - A Universal Evaluation Framework for Large Language Models

Explore a universal evaluation framework for large language models using Hierarchical Prompting Taxonomy. Gain insights into assessing dataset complexity and model capabilities.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences

Explore EvalGen, an interface for automated assistance in generating evaluation criteria and implementing assertions for LLM outputs aligned with human preferences.

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

Efficient Multi-Prompt Evaluation Explained

Explore PromptEval, a novel method for estimating LLM performance across multiple prompts, enhancing evaluation accuracy within practical budgets. Gain insights from University of Michigan researcher Felipe Polo.

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