The first part of this tutorial introduces the fundamental concepts and technologies behind internet‑delivered media. It provides an in‑depth overview of modern streaming formats and protocols, including MPEG‑DASH, HLS, CENC, CMAF, HTTP/3, QUIC, as well as relevant Web APIs such as Media Source Extensions (MSE), Encrypted Media Extensions (EME), and the Web Transport API. Particular emphasis is placed on the latest features and recent developments in these technologies.
In addition, this part explores the standardization activities of key organizations shaping the streaming ecosystem, including MPEG, SVTA, CTA‑WAVE, C2PA, and 5G‑MAG

Topics include:

• Streaming formats and protocols: MPEG‑DASH, HLS, CENC, CMAF, HTTP/3, QUIC
• Web Media APIs: Media Source Extensions (MSE), Encrypted Media Extensions (EME), Web Transport API
• Standardization acitivities: MPEG, SVTA, CTA‑WAVE, C2PA, and 5G‑MAG

The field of Extended Reality (XR) is rapidly evolving, driven by advances in streaming technologies, new XR platforms, and a growing diversity of XR devices. This tutorial provides an overview of the current state of XR streaming and its increasing importance for delivering immersive experiences across headsets and emerging smart glasses.

We will begin by examining the key technological trends shaping XR streaming, including cloud and edge rendering, low‑latency networks, and adaptive streaming techniques, and discuss their implications for scalable XR content delivery. The tutorial will then explore the role of XR streaming in supporting next‑generation XR experiences, with a focus on media, interactive applications, and virtual environments.

In the context of XR platforms and devices, we will discuss how Android XR and recent developments in Spatial Computing are influencing XR streaming architectures. In addition, the tutorial will provide an update on the latest XR devices, with particular emphasis on smart glasses and display‑enabled wearables, such as Meta Ray‑Ban Display glasses and upcoming Android XR‑based devices including Samsung Galaxy XR.

As AI becomes increasingly central to media workflows, understanding how modern models actually work is essential. This tutorial provides a clear, accessible, and technically grounded introduction to contemporary AI systems — with a special focus on neural networks, Transformer models, and Large Language Models (LLMs).

We unpack the mechanics behind today’s generative AI: how models process language, how attention works, what happens during training and inference, and why Transformers are so effective. Through intuitive explanations, visual breakdowns, and simplified examples, participants will gain a solid conceptual understanding of how modern AI systems operate “under the hood.”

Topics include:

• AI & Machine Learning Basics: Core concepts, model families, training principles
• Vectorization: Architecture, embeddings, tokenization, optimization
• The Transformer Model: Attention mechanisms, encoder/decoder structures, masking
• Capabilities & Limitations: Bias, hallucinations, safety constraints, model weaknesses
• Looking Ahead: Trends such as multimodal models and mixture of experts

This tutorial is ideal for participants who want to understand how modern AI and LLMs function.

The second part of the tutorial focuses on current and emerging innovations in streaming technology. It presents a selected set of trending topics such as Media over QUIC, 5G Media Streaming, L3D DASH, CMCD version 2, Server‑Guided Ad Insertion, and Green Streaming.
Whenever possible, the concepts are complemented by short live demonstrations, with a particular focus on playback using the DASH reference player dash.js.

Topics include:

• Trending topics: Media over QUIC, 5G Media Streaming, Low Latency Low Delay (L3D) DASH, Common Media Client Data (CMCD) Version 2, Server‑Guided Ad Insertion (SGAI), and Green Streaming
• Live demonstrations: dash.js

As digital media becomes increasingly tampered with, AI‑generated, and rapidly distributed, ensuring trust in content is more critical than ever. This tutorial offers a clear and technically grounded introduction to Provenance & Authenticity — why they matter, how they work, and how modern standards help verify the origin and integrity of media.

Drawing on real‑world examples and intuitive explanations, the session demystifies how provenance metadata is created, maintained, verified, and protected across the media lifecycle. Participants will learn why misinformation, deepfakes, and content manipulation have become systemic challenges — and how emerging technologies address them.

Topics include:

• Why Provenance Matters Today: The rise of misinformation, disinformation, deepfakes, and synthetic media — and how trust in digital ecosystems is eroding.
• Core Concepts of Provenance & Authenticity: What provenance means in a media context: origins, editing history, ownership, and the “trust trail” of content.
• Foundations of Media Provenance: How metadata, signatures, and provenance chains capture how content evolves during production and publishing.
• Technical Underpinnings: How provenance information is structured, validated, and linked.
• Challenges in Modern Media Landscapes: What makes trustworthy content verification difficult in distributed media environments.

Ideal for participants seeking a conceptual foundation in media provenance, this tutorial bridges the gap between why provenance is essential and how technical mechanisms ensure authenticity.

Building on the foundational understanding from the first tutorial, this session focuses on how to develop AI‑powered applications tailored to the media domain. It covers hands‑on methods, architectural approaches, and best practices for building robust, production‑ready AI systems.

Participants learn how to work effectively with LLMs — from prompting and orchestration to fine‑tuning and advanced retrieval techniques (RAG). We explore how to integrate multimodal models into production workflows, build intelligent assistants, and design agent‑based pipelines capable of handling complex tasks.

Topics include:

• LLM-Based Application Development: Prompting strategies, evaluation, orchestration
• Fine‑Tuning & Customization: Parameter‑efficient methods, domain adaptation
• Retrieval‑Augmented Generation (RAG): Document pipelines, vector databases, retrieval workflows
• AI Agents: Tool use, multi‑step reasoning, automation patterns
• Multimodal AI: Vision‑language models, video analysis, interactive media chatbots
• Hands‑On Use Cases:
  • Intelligent document‑based chatbots
  • Search & recommendation assistants
  • Video‑based conversational agents
  • Interview bots for expert knowledge capture
• Authenticity & Security: C2PA, provenance, compliance, responsible AI guidelines

This tutorial is designed for developers, media technologists, innovation leads, and anyone creating AI-driven applications in media environments.