Generative AI Workshop
Paper Submission Deadline: 04 August 2024, 11:59 pm AOE.
Recent progress in generative models have resulted in models that can produce realistic text, images and video that can potentially revolutionize the way humans work, create content and interact with machines. The workshop on Generative AI at AIMLSystems will focus on the entire life-cycle of building and deploying such Generative AI systems, including data collection and processing, developing systems and requisite infrastructure, applications it enables, and the ethics associated with such technology covering concerns related to fairness, transparency and accountability. We invite original, unpublished work on Artificial Intelligence with a focus on generative AI and their use cases. Specifically, the topics of interest include but are not limited to:
- Systems, architecture and infrastructure for Gen AI
- Foundation models and their applications
- Multi-modal Gen AI
- Retrieval Augmented Generated
- Gen AI based plugins and agents
- Learning from human preferences
- Evaluation of foundation models
- ML Ops for Gen AI
- Instruction tuning and instruction following
- Responsible Gen AI
- Large language model performance benchmarking
- Anupam Purwar, Senior Research Scientist, Amazon
- Hiteshi Sharma, Researcher II, Microsoft Research
Accepted Papers
1. Methodology for Quality Assurance Testing of LLM-based Multi-Agent Systems
Isha Shamim (Tata Consultancy Services Limited)*; Rekha Singhal (TCS)
2. Bridging the Gap: Synthetic Data Augmentation through Inversion and Distribution Matching for Few-shot Learning
Yunsung Chung (Tulane University)*; Janet Wang (Tulane University); Jihun Hamm (Tulane University)
3. Question-Answering System in Computer Science
Harshit Verma (BITS Pilani Hyderabad); M Bhargav (BITS Pilani Hyderabad); Ritvik – (BITS Pilani Hyderabad); Chetana Dr Gavankar (BITS Pilani)*; Prajna Devi Upadhyay (BITS Pilani Hyderabad)
4. Introducing a new hyper-parameter for RAG: Context Window Utilization
Kush Juvekar (Independant)*; Anupam Purwar (Independent)
Keynote Speakers
Dr. Aron Culotta
Tulane University, USA
Title
Co-creating Civic AI: Partnering Academia with Local Communities
Abstract
I’ll present ongoing work at Tulane’s Center for Community-Engaged AI partnering with local non-profits to build AI tools for transparency and accountability in criminal court and city government. I will first discuss our work with Eye on Surveillance, who have developed a retrieval-augmented generation tool over New Orleans city council transcripts (sawt.us). We have collaborated to use automated LLM evaluations and to engage with community users to improve the trustworthiness of the system. Second, I will discuss our work with Court Watch NOLA to build AI models for monitoring the equity in criminal court, including methods to estimating causal effects from text data. I will conclude with an overview of future directions in how generative AI can be used for a number of civic applications.
Bio
Dr. Culotta is an Associate Professor of Computer Science at Tulane University and Director of the Tulane Center for Community-Engaged Artificial Intelligence. He received his PhD in computer science from the University of Massachusetts-Amherst in 2008, and his research focuses on machine learning, natural language processing, and social network analysis, and their implications on society. His NSF-funded research has developed AI methods for several interdisciplinary projects in public health, marketing, political science, and emergency response. He has published over seventy academic articles on AI, serves on the steering committee of the International Conference on Web and Social Media, and has received best paper awards from the ACM Conference on Computer-Supported Cooperative Work and Social Computing and from the AAAI Conference on Artificial Intelligence.
Dr. Jihun Hamm
Tulane University, USA
Title
Can synthetic images be better than real images?
A study of utility and privacy of synthetic images in dermatology
Abstract
Advances in generative models such as GAN, VAE, and more recently, Diffusion models have revolutionized the field of image generation by enabling the generation of photorealistic synthetic images for many potential applications. Along with the advances, the question whether synthetic data can replace real data has become increasingly relevant. Synthetic data has been demonstrated to improve classification and to overcome the data scarcity issues such as data imbalance, robustness, and biases. This is done by generating synthetic data distributions with improved balance and other properties. Furthermore, there is an increasing demand for privacy-preserving synthetic image generation across various domains such as healthcare, finance, and social media. However, achieving the optimal tradeoff between utility and privacy remains a significant technical challenge, and various privacy-preserving techniques are being studied. In this talk, I will first discuss how generative AI can help in skin disease diagnosis problem, and also present benchmarking results on utility-privacy of recent image synthesis methods.
Bio
Dr. Jihun Hamm has been an Associate Professor of Computer Science at Tulane University since 2019. He received his PhD degree from the University of Pennsylvania in 2008 supervised by Dr. Daniel Lee. Dr. Hamm’s research interest is in machine learning, from theory to applications. He has worked on the theory and practice of robust and adversarial machine learning, privacy and security and optimization. Dr. Hamm also has worked on medical data analysis. His work in machine learning has been published in top venues such as ICML, NeurIPS, CVPR, JMLR, and IEEE-TPAMI. His work has also been published in medical research venues such as MICCAI, MedIA, and IEEE-TMI. Among other awards, he has earned the Best Paper Award from MedIA, Finalist for MICCAI Young Scientist Publication Impact Award, and Google Faculty Research Award.
Important note to authors about the new ACM open access publishing model
ACM has introduced a new open access publishing model for the International Conference Proceedings Series (ICPS). Authors based at institutions that are not yet part of the ACM Open program and do not qualify for a waiver will be required to pay an article processing charge (APC) to publish their ICPS article in the ACM Digital Library. To determine whether or not an APC will be applicable to your article, please follow the detailed guidance here: https://www.acm.org/
Further information may be found on the ACM website, as follows:
Full details of the new ICPS publishing model: https://www.acm.org/
Full details of the ACM Open program: https://www.acm.org/
Please direct all questions about the new model to [email protected].
Submission Guidelines
We invite authors to submit original and unpublished research papers (up to 4 pages excluding references). All submissions will undergo a rigorous peer-review process by the program committee. The authors are requested to follow the ACM sigconf template (see https://www.overleaf.com/gallery/tagged/acm-official). All accepted papers will be published in the proceedings of AIMLSys 2024.
Submission link: (please select the GenerateAI Workshop AI track).
Important Dates
- Paper Submission Deadline: 04 Aug 2024
- Notification of Acceptance: 24 Aug 2024
- Camera-Ready Deadline: 21 Sept 2024 (AoE)
- Workshop Date: 8 Oct 2024
- Conference Dates: October 8-11, 2024
Workshop Organization
The workshop will feature keynote speeches, technical paper and poster sessions, tutorials and possibly panel discussions. A detailed outline of the program would be available on the website shortly. The workshop would also provide ample opportunities for attendees to network with leading experts and well gain hands-on experience on Generative AI from tutorial sessions.
Registration
At least one author of an accepted paper will need to register for the conference and in case of multiple papers with the same author, co-authors need to register (1 unique registration by one of the authors per paper is required).
Workshop Venue
Energy, Coast and Environment Building
Louisiana State University, Baton Rouge, USA
Contact Information
For any inquiries regarding the workshop, please feel free to contact the workshop organizers.