3 citations · 8 across the 4 of their papers we have counts for
5 papers
Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs
Nafiseh Ghoroghchian, Haipeng Zhang, Shuyi Han +2
Despite the success of Time Series Foundation Models (TSFMs) on broad benchmarks, their ability to internalize basic temporal logic, especially in settings supported by exogenous c…
A Geometric Framework for Understanding Memorization in Generative Models
Brendan Leigh Ross, Hamidreza Kamkari, Tongzi Wu +5
As deep generative models have progressed, recent work has shown them to be capable of memorizing and reproducing training datapoints when deployed. These findings call into questi…
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
Antoni Kowalczuk, Jan Dubiński, Atiyeh Ashari Ghomi +6
Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these…
TabPFGen -- Tabular Data Generation with TabPFN
Junwei Ma, Apoorv Dankar, George Stein +2
Advances in deep generative modelling have not translated well to tabular data. We argue that this is caused by a mismatch in structure between popular generative models and discri…
Self-supervised Representation Learning From Random Data Projectors
Yi Sui, Tongzi Wu, Jesse C. Cresswell +5
Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. Whil…