319 citations · 1.2k across the 94 of their papers we have counts for
103 papers
Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior
Eliot Walt, Miltiadis Kofinas, Nikolaj Mücke +2
Deep learning has revolutionised weather forecasting in recent years, especially through atmospheric foundation models, which offer competitive skill for a fraction of the computat…
Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation
Dimitrios Karageorgiou, Symeon Papadopoulos, Ioannis Kompatsiaris +1
Autoregressive video diffusion models have enabled the generation of arbitrarily long videos by removing conditioning on future frames, thus greatly improving computational efficie…
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-…
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…
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…
Dual Guidance Semi-Supervised Action Detection
Ankit Singh, Efstratios Gavves, Cees G. M. Snoek +1
Semi-Supervised Learning (SSL) has shown tremendous potential to improve the predictive performance of deep learning models when annotations are hard to obtain. However, the applic…