From Theory to Practice: Workshop on Large Language and Foundation Models
Location: Online
Conference: BigData 2025 (IEEE International Conference on Big Data)
Date: December 9th, 2025
Large language and foundation models have rapidly emerged as pivotal technologies in data science and analytics, offering unprecedented capabilities in text generation, knowledge extraction, and complex decision-making. The third iteration of this workshop seeks to bridge cutting-edge theory with real-world applications, providing a venue for researchers and practitioners to exchange novel methodologies, deployment strategies, and impact-driven insights. By spot-lighting both breakthrough techniques and operational challenges, the workshop aims to foster cross-pollination of ideas, accelerate innovation, and elucidate pathways for seamless integration of large language models into diverse data-driven ecosystems.
- Submission Deadline: October 10th, 2025
- Paper Notification: November 3rd, 2025
- Paper Camera-Ready: November 13th, 2025
- Contact:
amllab[at]bit.uni-bonn.de
Workshop Agenda
The workshop will take place online on December 9th, 2025. Please note that the times are in Central European Time (CET).
| Time (CET) | Title | Presenter/Author |
|---|---|---|
| 13:00–13:15 | Welcome Words | |
| 13:15–13:45 | Large Language Models for Fault Diagnosis | Wensheng Gan |
| 13:45–14:15 | Quantifying and Mitigating Occupational Bias in Open-Source Large Language Models | Raghava Rao Mukkamala |
| 14:15–14:45 | Geometric Model Merging for Efficient and Scalable Adaptation of Large Language Models | Bikram Pratim Bhuyan |
| 14:45–15:15 | Optimizing Agentic Code Generation: Cost Efficiency, Observability and Orchestration | Alex Kaplunovich |
| 15:15–15:45 | Coffee Break | |
| 15:45–16:30 | Key Note: Cancelled | |
| 16:30–17:00 | CloudBot: Autonomous End-to-End Cloud Deployment from Code to Infrastructure | Oluwatobiloba Ódùnsì |
| 17:00–17:45 | Key Note: Cancelled | |
| 17:45–17:50 | Closing Remarks |
Submission
Papers should be submitted single blind.
Paper formats are:
- Long papers: up to 10 pages including all figures, tables, and references
- Short and vision papers: up to 6 pages including all figures, tables, and references
- Papers should be submitted single blind.
All papers must be submitted in the IEEE conference format:
- Official templates: https://www.ieee.org/conferences/publishing/templates.html
- Overleaf templates: https://www.overleaf.com/latex/templates/ieee-conference-template/grfzhhncsfqn
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 workshop papers will be published by IEEE in the BigData proceedings and will be submitted for inclusion in the IEEEXplore Digital Library.
Organizers
- Prof. Dr. Rafet Sifa (University of Bonn, Germany)
- Prof. Dr. Wei Liu (University of Technology Sydney, Australia)
- Dr. Dhavel Patel (IBM Research, USA)
- Tobias Deußer (Fraunhofer IAIS, Germany)
- Dr. Linsey Pang (Salesforce, USA)
- Dr. Lorenz Sparrenberg (University of Bonn, Germany)
Program Committee
- Farizeh Aldabbas, Fraunhofer IAIS, Germany
- Manuela Bergau, Fraunhofer IAIS, Germany
- Armin Berger, University of Bonn, Germany
- Hossam Elsafty, Fraunhofer IAIS, Germany
- Pranay Kona, Walmart, USA
- Deep Narayan Mishra, Walmart, USA
- Surya Lakshmi Sujitha Pasumarty, Albertsons, USA
- Corinna Schmalohr, Universitätsklinikum Bonn, Germany
- Dezhi Yu, UC Berkeley, USA