Program Overview

BBOmix: A Tabular Benchmark for Hyperparameter Optimization in Unsupervised Biological Representation Learning
Luca Thale-Bombien, Jan Ewald, Ralf König, Aaron KleinABCD Track

Evolutionary Architecture Search Through Grammar-Based Sequence Alignment
Adri Gómez, Felix Möller, Steven McDonagh, Monica Abella, Manuel Desco, Elliot J. Crowley, Aaron Klein, Linus EricssonMethods Track

OpenGNS: An Open Dataset of the Gradient Noise Scale across Vision, Language, and Diffusion Models
Marcel Aach, Jiangtao Wang, Stefan Kesselheim, Andreas LintermannABCD Track

Dynamic Priors in Bayesian Optimization for Hyperparameter Optimization
Lukas Fehring, Marcel Wever, Maximilian Spliethöver, Leona Hennig, Henning Wachsmuth, Marius LindauerMethods Track

Equally Good, Yet Different: Benchmarking Rashomon sets in AutoML packages
Katarzyna Woźnica, Katarzyna Rogalska, Zuzanna Sieńko, Mustafa CavusABCD Track

Auto-prepper: An Automated Data Preparation Toolkit for Real-world AutoML
Sasa Mladenovic, Marius Lindauer, Carola DoerrLate-Breaking Abstract Track

Efficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out Evaluation
Heinke HihnLate-Breaking Abstract Track

Automating Privacy-Constrained RAG Pipelines with AIP-1 and AIP-2
Gregor Molan, Martin MolanLate-Breaking Abstract Track

Automated Structure Learning for Predicting Influence Spread from Observed Cascades
Matic Požar, Miklós KrészLate-Breaking Abstract Track

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate
Blaž Bertalanič, Carolina FortunaHot-Off-the-Press Track

Algorithm Selection with Zero Domain Knowledge via Text Embeddings
Stefan SzeiderMethods Track

IBUS: Overcoming Structural Biases in Hierarchical NAS with Iterative Bottom-Up Sampling
Abay Artykbayev, Martin Rapp, Benedikt Staffler, Margret KeuperMethods Track

whittle: A Library for Sub-Network Extraction from Large Language Models
Arjun Krishnakumar, Rhea Sanjay Sukthanker, Hannan Javed Mahadik, Gabriela Kadlecová, Vladyslav Moroshan, Timur Carstensen, Frank Hutter, Aaron KleinABCD Track

Tabular-DC-Bench: A Large-Scale Meta-Dataset for Hyperparameter Optimization in Deep Clustering
Mamdouh Aljoud, Gabriel Marques Tavares, Sandra Gilhuber, Collin Leiber, Thomas SeidlABCD Track

All papers presented on Monday are also presented as posters in Poster Session I.

FS-DCM: Frequency-Separated Dual-Context Modeling with Dynamic Local Volatility Weighting for Time-Series AutoML
Jonghyun Lee, Moonsu KimMethods Track

NATS-Bench-MCU: A Tabular Hardware Benchmark for Neural Architecture Search on Microcontrollers
Sebastian Zimmermann, René Groh, Andreas M KistABCD Track

Towards Predicting Hyperparameter Importance from Dataset Meta-Features
Maha Ksouri, Daphne Theodorakopoulos, Marius LindauerMethods Track

A Large-Scale Study of Overtuning Mitigation Strategies in Hyperparameter Optimization
Sietse Schröder, Zubin Zellmann, Matthias Feurer, Mitra Baratchi, Jan N. van Rijn, Bernd BischlMethods Track

MLJAR AutoML: Transparent and Fairness-Aware AutoML for Tabular Data with Automatic Documentation
Aleksandra Płońska, Piotr PłońskiABCD Track

ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
Shiwen Qin, Alexander Auras, Shay B Cohen, Elliot J. Crowley, Michael Moeller, Linus Ericsson, Jovita LukasikMethods Track

Synthesizing Feature Extractors: An Agentic Approach for Algorithm Selection
Hai Xia, Carlos Ansótegui, Stefan SzeiderMethods Track

Efficient ensemble inference
Nick Kocher, Janek Paeßens, Anja Jankovic, Holger H. HoosMethods Track

An Open-Source Training Dataset for Foundation Models for Hyperparameter Optimization
Aaron Klein, Herilalaina Rakotoarison, Luca Thale-Bombien, David SalinasLate-Breaking Abstract Track

Flow of solution procedure in DARTS for robust neural architecture search
Yitong Guo, Marie Anastacio, Jan N. van Rijn, Holger HoosLate-Breaking Abstract Track

Invariance of Violation-Ranking Maps in Constrained Black-Box Optimization
Kaichi Irie, Shuhei Watanabe, Kaito BabaLate-Breaking Abstract Track

Heterogeneous Structured Pruning under Resource Constraints for Hardware Efficient LLMs
Cameron Barker, Andreas Paraskeva, Jan N. van Rijn, Elliot J. Crowley, Henry GoukLate-Breaking Abstract Track

MOEns: Multi-Objective Post-Hoc Ensembling for Predictive Accuracy and Adversarial Robustness in AutoML
Berkay Akay, Marie Anastacio, Jan N. van Rijn, Holger HoosLate-Breaking Abstract Track

Learning to Solve and Optimize by Evolving Code
Veronika Semmelrock, Benedetta Strizzolo, Francesco Zuccato, Gerhard Friedrich, Patrick Rodler, Konstantin SchekotihinLate-Breaking Abstract Track

TabPFN-ScAn-Bench: A Surrogate Benchmark for Scaling Analysis Algorithms
Nastaran Alipour, Donat Sinani, Artin Sermaxhaj, Johannes Hog, Danny StollLate-Breaking Abstract Track

α-PFN: Fast Entropy Search via In-Context Learning
Herilalaina Rakotoarison, Steven Adriaensen, Tom Julian Viering, Carl Hvarfner, Samuel Müller, Frank Hutter, Eytan BakshyHot-Off-the-Press Track

All papers presented on Tuesday are also presented as posters in Poster Session II.

Large Language Models for Automated Cross-Domain Machine Learning Task Type Identification: A Benchmark Dataset and Evaluation
Petros Tsialis, Steffen Limmer, Tobias Rodemann, Martin HeckmannMethods Track

Does Preprocessing Quality Matter for AutoML? A Case Study on Time Series Forecasting with Environmental Data
Guilherme Castro Dallasta, Jan N. van Rijn, Andre Carlos Ponce de Leon Ferreira De CarvalhoABCD Track

Transfer Learning of Robustness for Image Classification: An Experimental Study using Robustness Distributions
David P. Wünsch, Annelot Willemijn Bosman, Holger H. Hoos, Jan N. van RijnMethods Track

Zero-Shot Bayesian Optimization with TabPFN: Competitive with State-of-the-Art without Per-Task Training
Theodore Rogers, Srividya PonnadaMethods Track

SNAC-Pack 2.0: Scaled-Out Surrogate Neural Architecture Codesign
Jason Weitz, Dmitri Demler, Benjamin Hawks, Aaron Wang, Nhan Tran, Javier DuarteABCD Track

TACTICL: Task-Aware Compression of Tabular ICL Models
Mykhailo Koshil, Matthias Feurer, Katharina EggenspergerMethods Track

SAMLB: A Streaming AutoML Benchmark
Nilesh Verma, Albert Bifet, Bernhard Pfahringer, Maroua BahriABCD Track

From Tables to Runtime: Predicting Algorithm Runtime Distributions with TabPFN
Hagverdi Ibrahimli, Katharina Eggensperger, Steven AdriaensenMethods Track

Hyperparameter Optimization in the Age of Large Models
Erlis Lushtaku, Ali Elganzory, Danny StollLate-Breaking Abstract Track

Search More or Confirm Better? Reliable Selection in Small-Budget LoRA Hyperparameter Optimization
Pece Georgiev, Biljana TojtovskaLate-Breaking Abstract Track

Towards Unifying AutoML: Introducing Neural Pipeline Search Spaces
Lum Birinxhiku, Anton Geburek, Steven Adriaensen, Danny StollLate-Breaking Abstract Track

ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
David Rundel, Fabian Fumagalli, Maximilian Muschalik, Bernd Bischl, Matthias FeurerHot-Off-the-Press Track

Semi-supervised learning from tabular data with autoencoders: when does it work?
Sintija Stevanoska, Jurica Levatić, Sašo DžeroskiHot-Off-the-Press Track

All papers presented on Wednesday are also presented as posters in Poster Session III.