Deep Learning
Lower Bounds on Adversarial Robustness from Optimal Transport
Arjun Nitin Bhagoji, Daniel Cullina, Prateek Mittal
We apply our framework to the case of Gaussian data with norm-bounded adversaries and explicitly show matching bounds for the classification and transport problems as well as the optimality of linear classifiers.
Non-convolutional Graph Neural Networks
Interestingly, most of these works are either not applicable to, or have not been tested on, node-level tasks.
LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation Y ujie Lu
Notably, our LLMScore achieves Kendall's
ImprovingCoherenceandConsistencyinNeural SequenceModelswithDual-System, Neuro-SymbolicReasoning
Human reasoning can be understood as an interplay between two systems: the intuitiveandassociative("System1")andthedeliberativeandlogical("System2").
empty PointMamba: A Simple State Space Model for Point Cloud Analysis
PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs.