1

CiteME: Can Language Models Accurately Cite Scientific Claims?
Thousands of new scientific papers are published each month. Such information overload complicates researcher efforts to stay current …
Ori Press, Andreas Hochlehnert, Ameya Prabhu, Vishaal Udandarao, Ofir Press, Matthias Bethge
PDF Code Project
CiteME: Can Language Models Accurately Cite Scientific Claims?
Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli
Motion is a crucial cue for human object perception. Previous studies have demonstrated that humans can recognize objects even in …
Matthias Tangemann, Matthias Kümmerer, Matthias Bethge
Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models
With the advent and recent ubiquity of foundation models, continual learning (CL) has recently shifted from continual training from …
Lukas Thede, Karsten Roth, Olivier J. Henaff, Matthias Bethge, Zeynep Akata
PDF
Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models
Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
The ability of machine learning systems to learn continually is hindered by catastrophic forgetting, the tendency of neural networks to …
Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge
PDF Code Dataset Project Video
Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
In the last decade, the generalization and adaptation abilities of deep learning models were typically evaluated on fixed training and …
Fırat Öncel, Matthias Bethge, Beyza Ermis, Mirco Ravanelli, Cem Subakan, Çağatay Yıldız
PDF
Modulated Neural ODEs
Neural ordinary differential equations (NODEs) have been proven useful for learning non-linear dynamics of arbitrary trajectories. …
Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves
PDF Code
The Entropy Enigma: Success and Failure of Entropy Minimization
Entropy minimization (EM) is frequently used to increase the accuracy of classification models when they’re faced with new data …
Ori Press, Ravid Shwartz-Ziv, Yann LeCun, Matthias Bethge
PDF Code
The Entropy Enigma: Success and Failure of Entropy Minimization
RDumb: A simple approach that questions our progress in continual test-time adaptation
Test-Time Adaptation (TTA) allows to update pre-trained models to changing data distributions at deployment time. While early work …
Ori Press, Steffen Schneider, Matthias Kümmerer, Matthias Bethge
PDF Code
RDumb: A simple approach that questions our progress in continual test-time adaptation
Unsupervised object learning via common fate
Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling. We …
Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf
PDF Code