FOURTH WORKSHOP ON LARGE LANGUAGE AND FOUNDATION MODELS
(WLLFM 2026)

Location: Sheraton Phoenix Downtown, Phoenix, AZ, USA

Conference: BigData 2026
(IEEE International Conference on Big Data)

Date: December 14–17, 2026

ABOUT THE WORKSHOP

Large language models (LLMs) and foundation models (FMs) have rapidly emerged as pivotal technologies in data science and analytics, offering unprecedented capabilities in text generation, knowledge extraction, and complex decision-making.

However, a significant gap remains between the rapid theoretical advancements in these models and their robust, scalable deployment in industrial environments.

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 spotlighting both breakthrough techniques and operational challenges—such as scalability, interpretability, and ethics—the workshop aims to foster cross-pollination of ideas and accelerate the seamless integration of large language models into diverse data-driven ecosystems.

IMPORTANT DATES

Submission deadline: October 26, 2026

Paper notification: November 9, 2026

Camera-ready deadline: November 21, 2026

All dates are AoE (Anywhere on Earth).

CONTACT

Email: amllab[at]bit.uni-bonn.de

SUBMISSION

Submission link:

https://wi-lab.com/cyberchair/2026/bigdata26/scripts/submit.php?subarea=S22&undisplay_detail=1&wh=/cyberchair/2026/bigdata26/scripts/ws_submit.php
Papers must be submitted using a single-blind review format.

Paper formats:

Long papers:

Up to 10 pages, including all figures, tables, and references.

Short and vision papers:

Up to 5 pages, including all figures, tables, and references.

All papers must use the IEEE conference format.

Official IEEE templates:

https://www.ieee.org/conferences/publishing/templates.html
Overleaf template:

https://www.overleaf.com/latex/templates/ieee-conference-template/grfzhhncsfqn
CALL FOR PAPERS

Topics of interest include, but are not limited to, the following:

STATE-OF-THE-ART MODEL RESEARCH

• Model training, optimization, and architecture

• Architectures beyond the Transformer, including state-space models, linear-attention variants, hybrid designs, and diffusion language models

• Reasoning models and test-time compute scaling

SYSTEMS AND EFFICIENCY

• Inference at scale: efficiency, latency, memory use, routing, and serving-time optimization for large models, including long-context and sparse architectures

• Efficient fine-tuning, adaptation, and post-training of LLMs or FMs, including supervision design, synthetic data, reward signals, preference optimization, distillation, and curated training pipelines

• Industrial use cases and challenges involving latency, cost optimization, and hardware constraints

RETRIEVAL AND CONTEXT MANAGEMENT

• Methods for obtaining, selecting, organizing, and using external information through retrieval, reranking, and context construction

• Retrieval-Augmented Generation (RAG) in enterprise environments

AGENTIC AND MULTI-AGENT SYSTEMS

• Multi-agent LLM systems and orchestration, including role specialization, agent-to-agent protocols, and standards such as MCP for tool integration

• Autonomous software-engineering agents and LLM-driven code generation in production codebases

MULTIMODAL AND DOMAIN-SPECIFIC FOUNDATION MODELS

• Multimodal and any-to-any foundation models spanning vision, audio, and video

• Foundation models for structured big-data modalities, including time-series, tabular, graph, and geospatial data

• Domain-specific foundation models for finance, healthcare, legal applications, and scientific discovery, including specialized constraints and metrics

• Quantum foundation models

PRIVACY, SAFETY, AND ETHICS

• Privacy-preserving and federated training or inference for LLMs and FMs

• Evaluation and trustworthiness, including robustness, reliability, safety, long-context behavior, and “in-the-wild” usefulness beyond narrow benchmark scores

• Interpretability and explainability of foundation models in decision-critical systems

• Ethical, societal, and regulatory considerations in LLM adoption

PROCEEDINGS AND INDEXING

All accepted workshop papers will be published by IEEE in the BigData 2026 Proceedings and submitted for inclusion in the IEEE Xplore Digital Library.

ORGANIZERS

• Prof. Dr. Rafet Sifa
University of Bonn / Fraunhofer IAIS, Germany

• Dr. Tobias Deußer
University of Bonn, Germany

• Prof. Dr. Aurelio Bariviera
University of Rovira i Virgili, Spain

• Dr. Dhaval Patel
IBM Research, USA

• Prof. Dr. Wei Liu
University of Technology Sydney, Australia

• Dr. Lorenz Sparrenberg
University of Bonn, Germany

• Dr. Linsey Pang
PayPal, USA

• Dr. Thore Gerlach
European Space Agency, Netherlands