From Standard Transformers to Modern LLMs: Bringing Dialogue Models, RAG, and Agents to the Classroom
Year: 2026
Type: conference-paper
Abstract: Modern LLM education is increasingly centered on system building: grounding generation with retrieval, enabling tool use, and deploying models under latency and cost constraints.We present an updated release of our open course on Transformer-based LLMs and multimodal models (Nikishina et al., 2024).The update introduces topics that have become important since the first edition: a session on Retrieval-Augmented Generation (RAG), a hands-on session on tool-using agents, an API-based track for applied work with LLMs, and practical local inference with vLLM.We also add a dedicated session on multimodal dialog models with a focus on dialog grounding.Incorporating the course with a discussion on longcontext transformers, focusing on KV-cache efficiency along with the related models and benchmarks, completes the system-building course update, suitable for various audiences.All materials are released online. 1
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: gold
OpenAlex ID: W7140140623