Education
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
Despite being a key challenge, task confusion lacks a theoretical understanding.
Metric Transforms and Low Rank Representations of Kernels for Fast Attention
This suggests that the low-rank fast attention only works for functions approx-imable by polynomials.
Loss landscape Characterization of Neural Networks without Over-Parametrization
In order to address this limitation, we propose a novel class of functions that can characterize the loss landscape of modern deep models without requiring extensive over-parametrization and can also include saddle points.
529d8b3a23991e83db07f21727256374-Paper-Datasets_and_Benchmarks_Track.pdf
To evaluate MLLMs' A VR abilities systematically, we introduce
Learning to Understand: Identifying Interactions via the Mobius Transform
One of the key challenges in machine learning is to find interpretable representations of learned functions.