Welcome and Introduction

Coupling HPC Plasma Simulations and AI at Exascale

• Michael Bussmann (Helmholtz-Zentrum Dresden-Rossendorf (HZDR))

We present recent results on coupling plasma simulations and large-scale AI models on exascale HPC systems and argue that the workflows we are implementing are the future of I/O.

Q&A

• Michael Bussmann (Helmholtz-Zentrum Dresden-Rossendorf (HZDR))

PhysicsNeMo

• Abouzar Ghasemi (NVIDIA)

NVIDIA PhysicsNeMo is an open-source Physics-Informed Machine Learning (Physics-ML) platform. It enables the creation of high-precision, physically based digital twins. - [Predict the time evolution of electric field magnitude inside shielded enclosures][1] - [AI-Driven Prediction of Epoxy Underfill Flow: Capturing Interface Dynamics in a Two-Phase System][2] [1]: https://github.com/ghasemiAb/physicsnemo/tree/EM_wave/examples/cfd/enclosure_shielding [2]: https://github.com/ghasemiAb/physicsnemo/tree/underfill-ag/examples/cfd/underfill_dispensing

Q&A

• Abouzar Ghasemi (NVIDIA)

Machine Learning Across Space and Time in Microscopy

• Martin Weigert (TU Dresden)

Modern microscopes generate large, information-dense images across space and time, challenging current vision models. I will present our work on machine learning for quantitative microscopy, including segmentation of complex biological images, self-supervised learning from videos, and multiscale vision transformers that integrate fine detail with broader biological context.

Q&A

• Martin Weigert (TU Dresden)

NVIDIA Cosmos und NVIDIA Omniverse

• Pallavi Mohan (NVIDIA)

NVIDIA Cosmos and NVIDIA Omniverse work hand-in-hand to form the cohesive ecosystem for Physical AI, Omniverse (The Infrastructure and Simulation Environment): Omniverse serves as the base and virtual "data space". Here, physically correct digital twins are created, physical laws are simulated, and environments (e.g., factories, road networks) are mapped using the OpenUSD standard. Cosmos (The World Foundation Models): Cosmos is the AI model platform that interacts directly with the 3D worlds from Omniverse. Cosmos consists of powerful models such as Cosmos Predict (for simulating world states), Cosmos Transfer (for photorealism), and Cosmos Reason (for physical understanding and decision-making).

Q&A

• Pallavi Mohan (NVIDIA)

LLM + Reasoning, Fine-Tuning

• Michael Färber (TU Dresden)

tbc.

Q&A

LLM and Fine Tuning/Inference

• Nael Fasfous (NVIDIA)

At NVIDIA, LLM fine-tuning is the process by which an already pre-trained base model (such as Llama, Mistral, or the in-house NeMo models) is further trained with specific, company- or task-specific data. NVIDIA provides a complete software infrastructure based on NVIDIA NeMo (an open-source framework for developing LLMs) as well as highly optimized hardware (such as NVIDIA GPU systems and Tensor cores).

Q&A

• Nael Fasfous (NVIDIA)

Conclusion & Outlook - Wrap up

CIDS Science Forum and Q&A The CIDS Science Forum is designed to foster collaboration and idea exchange beyond structural boundaries - at CIDS and beyond. Join us for an exciting opportunity to engage with our international partners as they present their cutting-edge research in TUD- and DDc-public lectures hosted by various CIDS departments. This forum aims to create a vibrant space for discussion, inspiration, and the sharing of diverse perspectives.