23 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Stony Brook UniversityUS3 papers
- University of BolognaIT3 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di BolognaIT2 papers
- University of AlbertaCA2 papers
- University of TorontoCA2 papers
- Arizona State UniversityUS1 paper
- Australian National UniversityAU1 paper
- Ben-Gurion University of the NegevIL1 paper
- Boğaziçi UniversityTR1 paper
- Brandenburg University of Technology Cottbus-SenftenbergDE1 paper
- Brown UniversityUS1 paper
- California Institute of TechnologyUS1 paper
9 papers
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Synthetic Polarization Maps of an Outflow Zone from Magnetohydrodynamic Simulations
Gianfranco Bino, Shantanu Basu, Masahiro N Machida +4
The canonical theory of star formation in a magnetized environment predicts the formation of hourglass-shaped magnetic fields during the prestellar collapse phase. In protostellar…
Better Long-Range Dependency By Bootstrapping A Mutual Information Regularizer
Yanshuai Cao, Peng Xu
In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data. Applied on language modelling, our regularizer expresses the inducti…
On the Sensitivity of Adversarial Robustness to Input Data Distributions
Gavin Weiguang Ding, Kry Yik Chau Lui, Xiaomeng Jin +2
Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this…
Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
Yanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui +1
We propose a novel regularizer to improve the training of Generative Adversarial Networks (GANs). The motivation is that when the discriminator D spreads out its model capacity in…
Online and Offline Analysis of Streaming Data
Sheik Hoque, Andriy Miranskyy
Online and offline analytics have been traditionally treated separately in software architecture design, and there is no existing general architecture that can support both. Our ob…
A Novel Approach to the Cosmological Constant Problem
Alberto Iglesias, Zurab Kakushadze
We propose a novel infinite-volume brane world scenario where we live on a non-inflating spherical 3-brane, whose radius is somewhat larger than the present Hubble size, embedded i…
Diluting solutions of the cosmological constant problem
Olindo Corradini, Alberto Iglesias, Zurab Kakushadze
We discuss the cosmological constant problem in the context of higher codimension brane world scenarios with infinite-volume extra dimensions.
Toward Solving the Cosmological Constant Problem?
Olindo Corradini, Alberto Iglesias, Zurab Kakushadze
We discuss the cosmological constant problem in the context of higher codimension brane world scenarios with infinite-volume extra dimensions. In particular, by adding higher curva…