1 citations · 1 across the 15 of their papers we have counts for
16 papers
Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies
Dalton Raphael Harmsen, Swier Garst, Thomas van Osch +2
Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingual pre-training, as prior work…
Croissant Tasks: A Metadata Format for Reproducible Machine Learning Evaluations
Omar Benjelloun, Leonardo Martins Bianco, Isabelle Guyon +8
Reproducibility is fundamental to the scientific method, yet remains a critical challenge in machine learning. Contributing factors include underspecified execution details and bri…
Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains
Hui Xie, Jie Liu, Ziyue Qiao +1
Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive…
Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin Vanschoren
The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear unders…
Automated Machine Learning for Unsupervised Tabular Tasks
Prabhant Singh, Pieter Gijsbers, Elif Ceren Gok Yildirim +2
In this work, we present LOTUS (Learning to Learn with Optimal Transport for Unsupervised Scenarios), a simple yet effective method to perform model selection for multiple unsuperv…
How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation
Prabhant Singh, Sibylle Hess, Joaquin Vanschoren
Transferability estimation metrics are used to find a high-performing pre-trained model for a given target task without fine-tuning models and without access to the source dataset.…
Meta-Learning Transformers to Improve In-Context Generalization
Lorenzo Braccaioli, Anna Vettoruzzo, Prabhant Singh +3
In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms t…
Occam's model: Selecting simpler representations for better transferability estimation
Prabhant Singh, Sibylle Hess, Joaquin Vanschoren
Fine-tuning models that have been pre-trained on large datasets has become a cornerstone of modern machine learning workflows. With the widespread availability of online model repo…
Unlocking [CLS] Features for Continual Post-Training
Murat Onur Yildirim, Elif Ceren Gok Yildirim, Joaquin Vanschoren
Continual learning requires models to integrate new classes or domains over time while preserving previously acquired knowledge. Within this paradigm, foundation models often achie…
On dataset transferability in medical image classification
Dovile Juodelyte, Enzo Ferrante, Yucheng Lu +3
Current transferability estimation methods designed for natural image datasets are often suboptimal in medical image classification. These methods primarily focus on estimating the…
Continual Learning on a Data Diet
Elif Ceren Gok Yildirim, Murat Onur Yildirim, Joaquin Vanschoren
Continual Learning (CL) methods usually learn from all available data. However, this is not the case in human cognition which efficiently focuses on key experiences while disregard…
Learning to Learn without Forgetting using Attention
Anna Vettoruzzo, Joaquin Vanschoren, Mohamed-Rafik Bouguelia +1
Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inh…
CLAMS: A System for Zero-Shot Model Selection for Clustering
Prabhant Singh, Pieter Gijsbers, Murat Onur Yildirim +2
We propose an AutoML system that enables model selection on clustering problems by leveraging optimal transport-based dataset similarity. Our objective is to establish a comprehens…
On Supernet Transfer Learning for Effective Task Adaptation
Prabhant Singh, Joaquin Vanschoren
Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new…
Unsupervised Meta-Learning via In-Context Learning
Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren +1
Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propo…
Self-Regulated Neurogenesis for Online Data-Incremental Learning
Murat Onur Yildirim, Elif Ceren Gok Yildirim, Decebal Constantin Mocanu +1
Neural networks often struggle with catastrophic forgetting when learning sequences of tasks or data streams, unlike humans who can continuously learn and consolidate new concepts…