7 papers
Universal Algorithm-Implicit Learning
Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner
Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literatu…
Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
Hoyeon Chang, Bálint Mucsányi, Seong Joon Oh
Neural networks adapt through first-order parameter updates, yet it remains unclear whether such updates preserve logical coherence. We investigate the geometric limits of the Line…
DISCO: Diversifying Sample Condensation for Efficient Model Evaluation
Alexander Rubinstein, Benjamin Raible, Martin Gubri +1
Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduc…
LLM generation novelty through the lens of semantic similarity
Philipp Davydov, Ameya Prabhu, Matthias Bethge +2
Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging. Existing evaluations ofte…
Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI
Elisa Nguyen, Johannes Bertram, Evgenii Kortukov +2
Explainable AI (XAI) aims to make AI systems more transparent, yet many practices emphasise mathematical rigour over practical user needs. We propose an alternative to this model-c…
Are We Done with Object-Centric Learning?
Alexander Rubinstein, Ameya Prabhu, Matthias Bethge +1
Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various…