A3D3 All-hands meeting

Session

Morning Plenary

14 Oct 2024, 09:00

Innovation Room (Convergence Center @ Purdue University)

1. Welcome

Seungbin Park, Yulei Zhang (University of Washington (US))

14/10/2024, 09:00

40. Efficient Multi-modal LLM on the Edge

Dr Song Han (MIT)

14/10/2024, 09:10

talk

This talk presents efficient multi-modal LLM innovations with algorithm and system co-design. I’ll first present VILA, a visual language model deployable on the edge. It is capable of visual in-context learning, multi-image reasoning, video captioning and video QA. Followed by SmoothQuant and AWQ for LLM quantization, which enables VILA deployable on edge devices, bringing new capabilities for...

45. Distribution Shifts in Graph Machine Learning and Graph Domain Adaptation

Pan Li

14/10/2024, 09:35

talk

Graphs have been widely applied to model intricate relationships among entities. The application of Graph Machine Learning (GML) to enhance prediction capabilities for graph-structured data is prevalent in several scientific disciplines, such as particle physics, material science, and biology. However, applications in these domains often present challenges due to changes in data distributions...

23. Trainee-led: Overview of MMA

Will Benoit

14/10/2024, 10:00

talk

Multi-messenger astronomy is one of the pillars of A3D3. It spans optical, neutrino, and gravitational wave astronomy, each of which is a field with exciting physics and the potential to apply advanced machine learning techniques. In this presentation, I will give an overview of the work that is currently being done across all of the groups in this area.

5. Trainee-led: Overview of Neuro

Seungbin Park

14/10/2024, 10:15

6. Trainee-led: Overview of HEP

Yuan-Tang Chou (University of Washington (US))

14/10/2024, 10:30

44. Trainee-led: Overview of HAC

Siqi Miao

14/10/2024, 10:45

talk

Algorithm and Hardware Co-Development (HAC) is a key focus area within A3D3, supporting the institute’s mission to build accelerated AI solutions for scientific discovery. Our team develops AI algorithms to address significant challenges in data-driven research, including data irregularity, label scarcity, and the complexity of understanding AI models, while also providing efficient hardware...

30. NSF HDR ML Anomaly Detection Challenge

Advaith Anand (University of Washington (US))

14/10/2024, 11:00

talk

Harnessing the Data Revolution (HDR), is an effort by the National Science Foundation (NSF) to promote the exploration of fundamental scientific questions using data-driven techniques. To raise interest in these approaches, and the HDR community, we have developed a Machine Learning (ML) challenge for anomaly detection, taking advantage of widespread data from several HDR institutes. This...

14. Introducing A3D3 trainee-union

3. Introduction to HDR ML Challenge

2. Plenary Speaker 1

Dr Song Han (MIT)

16. Plenary Speaker 2

Pan Li

15. Plenary Speaker 2

7. Trainee-led: Overview of HAC

Siqi Miao

4. Trainee-led: Overview of MMA

Will Benoit