1.1k citations · 2k across the 52 of their papers we have counts for
57 papers
Muting Tokens: Exploring Token Sparsification for Efficient Audio Transformers
Shreya Sajid, Fabrizio Julian Piva, Hiram Rayo Torres Rodriguez +3
Transformer-based models have shown strong performance across diverse tasks, but their reliance on self-attention mechanisms often leads to high computational costs. Token sparsifi…
Cross-Modal Forgetting and Transfer in Unified Multimodal Post-Training
Francesco Colasurdo, Ivan Slobozhan, Joaquin Vanschoren +1
Unified multimodal models answer questions about images and also generate images with one shared set of weights. This creates a post-training risk that single-purpose models do not…
How (and How Not) to Use Data Augmentation in VLA Post-Training
Bram Grooten, Joaquin Vanschoren
Vision-language-action (VLA) models currently demonstrate strong performance in a wide range of real-world robotics tasks. However, they often still lack the generalization ability…
On the Tightness and Computational Tractability of Higher-Dimensional Confidence Sequences
Fabian Denoodt, Sibylle Hess, Joaquin Vanschoren +1
Modern sequential monitoring problems often involve multiple metrics, where we monitor several data streams simultaneously and may act once the evidence is strong enough. Confidenc…
Evolving Machine Learning in Non-Stationary Environments: A Unified Survey of Drift, Forgetting, and Adaptation
Ignacio Cabrera Martin, Subhaditya Mukherjee, Almas Baimagambetov +2
In an era defined by rapid data evolution, traditional Machine Learning (ML) models often struggle to adapt to dynamic environments. Evolving Machine Learning (EML) has emerged as…
Introducing v0.5 of the AI Safety Benchmark from MLCommons
Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed +97
This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safe…
Croissant: A Metadata Format for ML-Ready Datasets
Mubashara Akhtar, Omar Benjelloun, Costanza Conforti +28
Data is a critical resource for machine learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that crea…
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
Branislav Pecher, Ivan Srba, Maria Bielikova +1
In few-shot learning, the selection of samples has a significant impact on the performance of the model. While effective sample selection strategies are well-established in supervi…
What Can AutoML Do For Continual Learning?
Mert Kilickaya, Joaquin Vanschoren
This position paper outlines the potential of AutoML for incremental (continual) learning to encourage more research in this direction. Incremental learning involves incorporating…
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
Luis Oala, Manil Maskey, Lilith Bat-Leah +35
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure developm…
Locality-Aware Hyperspectral Classification
Fangqin Zhou, Mert Kilickaya, Joaquin Vanschoren
Hyperspectral image classification is gaining popularity for high-precision vision tasks in remote sensing, thanks to their ability to capture visual information available in a wid…
Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates
Murat Onur Yildirim, Elif Ceren Gok Yildirim, Ghada Sokar +2
Continual learning (CL) refers to the ability of an intelligent system to sequentially acquire and retain knowledge from a stream of data with as little computational overhead as p…
Advances and Challenges in Meta-Learning: A Technical Review
Anna Vettoruzzo, Mohamed-Rafik Bouguelia, Joaquin Vanschoren +2
Meta-learning empowers learning systems with the ability to acquire knowledge from multiple tasks, enabling faster adaptation and generalization to new tasks. This review provides…
MALIBO: Meta-learning for Likelihood-free Bayesian Optimization
Jiarong Pan, Stefan Falkner, Felix Berkenkamp +1
Bayesian optimization (BO) is a popular method to optimize costly black-box functions. While traditional BO optimizes each new target task from scratch, meta-learning has emerged a…
AdaCL:Adaptive Continual Learning
Elif Ceren Gok Yildirim, Murat Onur Yildirim, Mert Kilickaya +1
Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to pr…
Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
Hilde Weerts, Florian Pfisterer, Matthias Feurer +7
The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducin…
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification
Ihsan Ullah, Dustin Carrión-Ojeda, Sergio Escalera +7
We introduce Meta-Album, an image classification meta-dataset designed to facilitate few-shot learning, transfer learning, meta-learning, among other tasks. It includes 40 open dat…
Are Labels Needed for Incremental Instance Learning?
Mert Kilickaya, Joaquin Vanschoren
In this paper, we learn to classify visual object instances, incrementally and via self-supervision (self-incremental). Our learner observes a single instance at a time, which is t…
Automated Imbalanced Learning
Prabhant Singh, Joaquin Vanschoren
Automated Machine Learning has grown very successful in automating the time-consuming, iterative tasks of machine learning model development. However, current methods struggle when…
Meta-Learning for Unsupervised Outlier Detection with Optimal Transport
Prabhant Singh, Joaquin Vanschoren
Automated machine learning has been widely researched and adopted in the field of supervised classification and regression, but progress in unsupervised settings has been limited.…
Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shifts
Tommie Kerssies, Mert Kılıçkaya, Joaquin Vanschoren
In this paper, our goal is to adapt a pre-trained convolutional neural network to domain shifts at test time. We do so continually with the incoming stream of test batches, without…
AMLB: an AutoML Benchmark
Pieter Gijsbers, Marcos L. P. Bueno, Stefan Coors +5
Comparing different AutoML frameworks is notoriously challenging and often done incorrectly. We introduce an open and extensible benchmark that follows best practices and avoids co…
DataPerf: Benchmarks for Data-Centric AI Development
Mark Mazumder, Colby Banbury, Xiaozhe Yao +42
Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithf…
Open-Ended Learning Strategies for Learning Complex Locomotion Skills
Fangqin Zhou, Joaquin Vanschoren
Teaching robots to learn diverse locomotion skills under complex three-dimensional environmental settings via Reinforcement Learning (RL) is still challenging. It has been shown th…