ECML PKDD 2026 Workshop

Is Bigger Always Better? (IBAB)

Model Capacity for Task-Specific AI: Theory, Practice, and Applications
September 2026
Naples, Italy
Half-Day
This workshop is not yet confirmed. The proposal is currently under review.

Overview

Do we always need bigger models? As the AI community pushes toward ever-larger architectures, a fundamental question remains underexplored: How much model capacity does a specific task actually require?

This workshop explores the fundamental question of how much capacity (in terms of parameters, architecture, and data) an AI model requires to effectively solve a specific task. This question is central to the ongoing community debate between large multi-task foundation models and smaller task-specific models. We will bring together researchers and practitioners from machine learning and a broad spectrum of applications, including but not limited to geosciences, healthcare, robotics, and biology to discuss theoretical foundations, empirical findings, and real-world applications. We welcome contributions to the full spectrum from TinyML on microcontrollers to Large Language Models, with a focus on principled approaches to right-sizing AI systems. Ideally, workshop contributions should investigate for a specific application scenario or task the tradeoffs in various performance metrics, including but not limited to predictive performance, inference speed, energy efficiency or robustness.

Keywords: model capacity, model selection, multi-objective optimization, tinyML, green AI, domain-specific AI, small language models

Invited Speakers

Confirmed and invited speakers.

EB
Emmanuel Baccelli
INRIA / FU Berlin
DS
David Salinas
Ellis, University of Freiburg
JG
Jacek Gołębiowski
distil labs

Topics of Interest

We invite submissions on (but not limited to) the following topics.

Theory and Methodology

  • Theoretical and empirical bounds on model capacity (scaling laws, VC theory, PAC-Bayes)
  • Model selection and neural architecture search for right-sized models
  • Multi-objective optimization balancing accuracy, efficiency, robustness, and fairness
  • Benchmarks and evaluation protocols for capacity-performance trade-offs

Model Compression and Efficiency

  • Knowledge distillation, pruning, and quantization
  • TinyML and efficient models for edge devices and resource-constrained environments
  • Green AI: energy consumption, carbon footprint, and sustainability of model sizing decisions

Domain Applications

  • Geosciences: climate modeling, remote sensing, sensor networks
  • Healthcare: medical imaging, wearable diagnostics, clinical decision support
  • Robotics: manipulation and grasping, human-robot interaction
  • Biology: protein folding, genomic analysis, drug discovery
  • Other domains with specific capacity constraints or requirements

Empirical Studies

  • Comparative studies of small specialized models vs. large general-purpose models
  • Task-specific capacity analysis across model families
  • Case studies on deploying right-sized models in production

Important Dates

Mark your calendar.

Submission
June 5, 2026
Notification
June 27, 2026
Camera-Ready
July 10, 2026
Workshop
Sep 7 or 11, 2026

All deadlines are 23:59 AoE (Anywhere on Earth).

Submission Guidelines

Submission guidelines will be announced soon.

Workshop Schedule

Preliminary schedule — details to be confirmed.

09:00
Opening Remarks
09:10
Keynote Talk 1: Emmanuel Baccelli - "TinyML: Pushing the Limits of Model Capacity on Edge Devices"
09:30
Keynote Talk 2: David Salinas - "Multi-Objective Optimization for Robust and Efficient AI"
10:50
Keynote Talk 3: Jacek Gołębiowski - "Benchmarking Small Language Models"
Coffee Break and Poster Session
11:15
Contributed Talks (3 presentations)
12:00
Panel Discussion: "Is Bigger Always Better?"
12:30
Domain Breakout Groups (LLMs, Geosciences, Healthcare, Biology, Robotics)
12:50
Closing Remarks

Program Committee

Emmanuel Baccelli
INRIA, FU Berlin
Giovanni Zappella
AWS
Antonino Freno
ebay
David Salinas
University Freiburg
Jacek Golebiowski
distil labs
Alexander Binder
University Leipzig

Organizers

Helena Mihaljevic
Einstein Center Digital Future, HTW Berlin
Amy Siu
BHT Berlin
Felix Biessmann
BHT / Einstein Center Digital Future
Erik Rodner
HTW Berlin / Merantix Momentum
Kristian Hildebrand
BHT Berlin
Peter Gehler
Tübingen AI Center
Alexander Binder
University of Leipzig

PhD Organizing Team

Golzar Atefi
BHT
Pallavi Mitra
AUMOVIO
Vipin Singh
BHT Berlin
Mario Koddenbrock
HTW Berlin
Ricardo Knauer
HTW Berlin