collaborators

5 papers

cs.LG2026

Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise

John Myron Uy

Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly. This study tests whether unc…

cs.LG2026

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR

Giacomo Cignoni, Simone Magistri, Andrew D. Bagdanov +1

This paper explores Online Continual Self-Supervised Learning (OCSSL), a scenario in which models learn from continuous streams of unlabeled, non-stationary data, where methods typ…

cs.CV2026

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation

Donald Shenaj, Federico Errica, Antonio Carta

Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since…

cs.LG2026

Online Continual Learning for Time Series: a Natural Score-driven Approach

Edoardo Urettini, Daniele Atzeni, Ioanna-Yvonni Tsaknaki +1

Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge. Similarly, online time series forecasting (OTSF) is a real-world problem w…

cs.LG2025

Online Curvature-Aware Replay: Leveraging Order Information for Online Continual Learning

Edoardo Urettini, Antonio Carta

Online Continual Learning (OCL) models continuously adapt to nonstationary data streams, usually without task information. These settings are complex and many traditional CL method…