activity
20242026
collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2026

LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty

Christoforos N. Spartalis, Theodoros Semertzidis, Petros Daras +1

We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch. LoTUS smooths…

cs.LG2026

Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence

Wenzhe Yin, Zehao Xiao, Pan Zhou +4

Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize InfoNCE to maximize…

cs.LG2026

Towards Uniformity and Alignment for Multimodal Representation Learning

Wenzhe Yin, Pan Zhou, Zehao Xiao +4

Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-…

cs.LG2025

Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability

Leonard Bereska, Zoe Tzifa-Kratira, Reza Samavi +1

Neural networks achieve remarkable performance through superposition: encoding multiple features as overlapping directions in activation space rather than dedicating individual neu…

cs.LG2025

Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI

Christoforos N. Spartalis, Theodoros Semertzidis, Petros Daras +1

We introduce SAFEMax, a novel method for Machine Unlearning in diffusion models. Grounded in information-theoretic principles, SAFEMax maximizes the entropy in generated images, ca…

cs.LG2025

Mechanistic PDE Networks for Discovery of Governing Equations

Adeel Pervez, Efstratios Gavves, Francesco Locatello

We present Mechanistic PDE Networks -- a model for discovery of governing partial differential equations from data. Mechanistic PDE Networks represent spatiotemporal data as space-…