Tutorials

Hanoi, Vietnam  |  December 18–20, 2026  |  VinUniversity (VinUni)  |  www.rivf2026.org

RIVF 2026 will feature tutorials delivered by leading researchers and practitioners on emerging and important topics in computing and communication technologies.

Important Dates (Tentative)
Proposal Submission Deadline October 1, 2026
Acceptance Notification November 30, 2026
Conference Dates December 18–20, 2026

Accepted Tutorials

Serving LLMs Efficiently with vLLM: From Core Concepts to Real-World Optimization

vLLM has become the default open-source engine for serving LLMs, but most users treat it as a black box. This tutorial opens the box. The first half explains how vLLM actually works — the inference pipeline, KV cache, scheduling, and why these design choices matter. The second half shows how a team optimizes a serving engine in practice: how to find bottlenecks, tune kernels, manage memory and precision, and measure results honestly. Examples are drawn from Moreh-vLLM, Moreh's in-house vLLM development effort, but every technique is general and applies to any vLLM deployment.

Format: Half-day, four hours including a break, with hands-on labs Instructors: Dr. Thanh Tuan Dao, Loc Tran, and Anh Cao (Moreh Vietnam) Details: Schedule, labs and instructors

Hands-On Humanoid Robot Simulation With NVIDIA Isaac GR00T and Newton

A simulation-only laboratory for researchers, graduate students and robotics engineers. The first two hours adapt NVIDIA's AI Day Singapore Isaac GR00T lab: learners inspect a Unitree G1 apple-to-plate scene in Isaac Sim and Isaac Lab-Arena, work with demonstration data, and evaluate a GR00T 1.7 policy. The next two hours use Newton Fundamentals to build and control physics simulations. No physical robot is required.

Format: Half-day, four hours, hands-on, for up to 60 learners Instructors: Herman Wu and Dr. Quan Tran Minh (NVIDIA) Details: Schedule, labs and instructors

Adapting Vision-Language Models for Low-Resource Document Intelligence: A Vietnamese Case Study

A practical methodology for adapting vision-language models to document understanding when high-quality task-specific data is scarce. Vietnamese forms, invoices and administrative documents provide the running case study, while the methods apply to other low-resource languages and specialized document collections. The tutorial connects dataset engineering, supervised adaptation with LoRA and QLoRA, and controlled evaluation, so that participants can tell useful improvements from template memorization.

Format: Half-day, three and a half to four hours, lectures and guided practical exercises Instructor: Nguyen Vu Son Lam (CMC OpenAI) Details: Outline, schedule and instructor

Call for Tutorial Proposals

We welcome proposals for half-day or full-day tutorials on topics relevant to the RIVF 2026 research tracks. Tutorials provide an opportunity to educate conference attendees about specific topics or technologies. See Call for Tutorials for the proposal format and submission instructions.

Contact

For inquiries, please contact: rivf2026@vinuni.edu.vn