From Theory to Practice: Special Session on Large Language and Foundation Models

Location: Pride Plaza Hotel, Aerocity, New Delhi, India
Conference: DSAA 2026 (IEEE International Conference on Data Science and Advanced Analytics)
Date: October 6–9, 2026 (special session slot: TBA)

Foundation models and large language systems have become indispensable technologies in data science and analysis, opening up powerful possibilities in the areas of text generation, knowledge extraction, and complex decision-making. This special session bridges the gap between theoretical breakthroughs and practical applications, creating a platform for researchers and practitioners to present innovative methods, exchange deployment strategies, and discuss actionable insights. By focusing on both technology and practical challenges, the session promotes interdisciplinary exchange, drives research momentum, and identifies effective approaches for embedding large language models in data-driven applications across various fields.

• Submission deadline: May 30, 2026
• Paper notification: August 10, 2026
• Camera-ready: August 30, 2026
• Contact: amllab@bit.uni-bonn.de

Aims and Scope

This special session examines the deployment of large language and foundation models across diverse application areas:

• Showcase state-of-the-art developments in model architecture, optimization, and computational approaches.
• Present practical implementations and challenges encountered when adopting large language models in industrial applications.
• Enable interdisciplinary collaborations that merge fundamental research insights with operational deployment strategies.
• Provide a collaborative space to deliberate on ethics, privacy, social impact, and compliance requirements stemming from large language and foundation model implementations.

Agenda

Program for SSLLFM 2026: TBA.

Time	Paper / Speaker	Presenter
TBA	TBA	TBA

Keynotes

Keynotes for SSLLFM 2026: TBA.

Submission

To submit a paper to SSLLFM2026, go to OpenReview (IEEE DSAA 2026 Conference), and select the “Special Session: From Theory to Practice: Special Session on Large Language and Foundation Models” track when it is available.

The length of each paper submitted to SSLLFM2026 should be no more than ten (10) pages and should be formatted following the standard 2-column U.S. letter style of IEEE Conference template. For further information and instructions, see the IEEE Proceedings Author Guidelines.

All submissions will be double-blind reviewed by the Program Committee based on technical quality, relevance to the special session’s topics of interest, originality, significance, and clarity. Author names and affiliations must not appear in the submissions, and bibliographic references must be adjusted to preserve author anonymity. Submissions failing to comply with paper formatting and authors anonymity will be rejected without reviews.

Because of the double-blind review process, non-anonymous papers that have been issued as technical reports or similar cannot be considered for SSLLFM2026. An exception to this rule applies to arXiv papers that were published in arXiv at least a month prior to SSLLFM2026 submission deadline. Authors can submit these arXiv papers to SSLLFM2026 provided that the submitted paper’s title and abstract are different from the one appearing in arXiv.

Call for Papers

The topics of interest are, but not limited to:

• Model Training and Optimization:
  • Techniques to deal with hallucinations
  • Training data for LLMs
  • Efficient and stable techniques for training and finetuning LLMs
  • Scalable approaches for distributed model training
  • Middleware for scale out data preparation for LLM training
  • Workflow orchestration for end-to-end LLM life cycle
  • Resource management for compute and energy efficient model training
  • Representation learning
• Model Utilization and Integration:
  • Using LLMs effectively as tools for Reinforcement Learning or search
  • Enhancing LLM capabilities by using external tools such as search engines
  • Visual Prompt Tuning and in-context learning
  • Enable easy experimentation with high utilization to train foundational models in the cloud
  • Strategies to scale resources for training/fine-tuning foundational models
  • Instruction tuning including generation of instruction tuning data
  • Parallel training: data model tensor (attention and weights)
  • Distributed workflows for data cleansing and model usage (LangChain)
  • Principled AI
  • Investigating reasoning capabilities of LLMs
  • Retrieval Augmented Generation
  • Alternative architectures such as State Space Models
• Compact Language Models and Knowledge Distillation:
  • Knowledge representations for training small/compact language models
  • Evaluation of different teacher-student distillation and model compression strategies
  • Techniques for efficient data encoding to maintain linguistic properties in compact models
  • Deployment of lightweight models in resource-constrained environments
  • Case studies on the effectiveness in various NLP tasks
• Application-Specific Models:
  • Math LLMs
  • Multimodal Foundation Models
  • Trustworthy Foundation Models
  • Large-scale Visual Foundation Models
  • Timeseries foundation models for forecasting, prediction and control
  • Multi-Agent System using LLMs
  • Recommender systems using LLMs
  • Knowledge management using LLMs
• Knowledge Incorporation and Adaptation:
  • Approaches to deal with knowledge recency to effectively update knowledge within LLMs
  • Incorporating domain knowledge in LLMs
• Evaluation and Benchmarking:
  • Additional benchmarks to fill gap between human and automatic reference-based evaluation

Proceedings and Indexing

All accepted full-length special session papers will be published by IEEE in the DSAA main conference proceedings under its Special Session scheme. All papers will be submitted for inclusion in the IEEEXplore Digital Library.

Previous Editions

• SSLLFM 2025 (Special Session at IEEE DSAA 2025, Birmingham, UK. 35 submissions, 8 accepted papers, 60+ participants.)
• WLLFM 2025 (Workshop at IEEE BigData 2025, Macau SAR, China. 29 submissions, 5 accepted papers, 50+ participants.)
• WLLFM 2024 (Workshop at IEEE BigData 2024, Washington DC, USA. 55 submissions, 19 accepted papers, 100+ participants.)
• WLLFM 2023 (Workshop at IEEE BigData 2023, Sorrento, Italy. 31 submissions, 11 accepted papers, 50+ participants.)

Organizers

Prof. Dr. Rafet Sifa (Contact Person)
University of Bonn, Germany · rafet.sifa@bit.uni-bonn.de
Prof. Dr. Rafet Sifa is a leading researcher in AI and machine learning, with over 15 years of experience and a regular contributor to top-tier machine learning conferences. His research focuses on hybrid deep learning and large-scale analytics, with extensive publications on both theoretical and applied machine learning topics with a deep focus on representation learning. He co-organized the special session on Informed and Explainable Methods for Machine Learning at ICANN 2019, the three workshops on foundational and large language models at IEEE BigData (2023, 2024, 2025), a special session on Large Language and Foundation Models at IEEE DSAA 2025, and workshops on Bridging Neurons and Symbols for NLP and Knowledge Graphs Reasoning at COLING 2024 and 2025.

Prof. Dr. Wei Liu
University of Technology Sydney, Australia · wei.liu@uts.edu.au
Wei Liu is an Associate Professor of Machine Learning and Director of the Future Intelligence Research Lab at UTS. He holds a PhD in Machine Learning from the University of Sydney. His research spans generative AI, adversarial machine learning, cybersecurity, game theory, multimodal learning, NLP, and intrusion detection. He has earned 3 Best Paper Awards and a Most Influential Paper Award at PAKDD, and serves as senior PC member and area chair at KDD, AAAI, and ICDM.

Dr. Dhaval Patel
IBM Research, USA · dhaval.patel@ibm.com
Dr. Dhaval Patel is a research scientist specializing in AI model optimization and industrial applications. His work bridges fundamental research and real-world deployment, focusing on scalable machine learning solutions. He co-organized the previous workshops on foundational and large language models at IEEE BigData as well as the special session at DSAA 2025.

Dr. Linsey Pang
PayPal Inc., USA · panglinsey@gmail.com
Linsey Pang is a Distinguished Scientist at PayPal. Previously she was a Principal Machine Learning Scientist at Salesforce. Prior to this, she was a Principal Data Scientist at Walmart Lab. Prior to joining Walmart Lab, she worked as an applied scientist at eBay Inc. She finished her PhD degree in machine learning research at the University of Sydney. She co-organizes multiple workshops and tutorials at CIKM, KDD, and WSDM in top data mining conferences.

Dr. Lorenz Sparrenberg
University of Bonn, Germany · lsparren@uni-bonn.de
Dr. Lorenz Sparrenberg’s research focuses on large language models and their evaluation, robustness, and limitations. His recent work includes research on efficient inference of LLMs and empirical studies on their behavior in real-world settings, as well as publications on representative learning for clinical and decision support applications including dementia detection and diabetic retinopathy.

Priya Tomar
University of Bonn, Germany · ppriya@uni-bonn.de
Priya is a data scientist at Fraunhofer IAIS and a PhD candidate at the University of Bonn focusing on deep learning-based medical image analysis, in particular Surgical AI. Her work addresses domain-specific challenges in the surgical domain by developing data-driven and application-oriented methods to enhance clinical applicability. Her recent publications focus on semantic segmentation for robot-assisted abdominal surgery.

Program Committee

• Lucie Flek, Lamarr Institute for Artificial Intelligence and Machine Learning, Germany
• Christian Bauckhage, Lamarr Institute for Artificial Intelligence and Machine Learning, Germany
• Ozlem Uzuner, George Mason University, USA
• Tobias Deußer, University of Bonn, Germany
• Armin Berger, University of Bonn, Germany
• Manuela Bergau, Fraunhofer IAIS, Germany
• Farizeh Aldabbas, Fraunhofer IAIS, Germany
• Johannes Radu Hübers, Fraunhofer IAIS, Germany
• Aashish Jain, Salesforce, USA
• Zian Wang, Stony Brook University, USA
• Qiushui Xu, Penn State University, USA
• Qikai Yang, University of Illinois Urbana-Champaign, USA
• Zheng Liu, Northeastern University, USA
• Tingting Tang, University of Southern California, USA
• Bo Yuan, Georgia Institute of Technology, USA
• Yunzhe Wang, University of Southern California, USA
• Yong Liu, Salesforce, USA
• Mounika Kamsali Veera, Walmart, USA
• Lisa Pucknat, AXA, Germany
• Pengfei Li, Visa Research, USA
• Surya Lakshmi Sujitha Pasumarty, Albertsons, USA
• Yingfan Wang, Duke University, USA
• Tian Long Xu, Squirrel AI Learning, USA
• Hao Yan, George Mason University, USA
• Mingxuan Yang, Brown University, USA
• Dezhi Yu, University of California, Berkeley, USA
• Haodong Zhang, New York University, USA