5.2k citations
- SupélecFR440 papers
- University of Applied Sciences and Arts of Southern SwitzerlandCH440 papers
- New York UniversityUS44 papers
- Princeton UniversityUS15 papers
- Google (United States)US13 papers
- Courant Institute of Mathematical SciencesUS11 papers
- Meta (Israel)IL11 papers
- Massachusetts Institute of TechnologyUS8 papers
- University of California, BerkeleyUS8 papers
- Stanford UniversityUS7 papers
- Carnegie Mellon UniversityUS6 papers
- Cornell UniversityUS6 papers
447 papers
Psyzkaller: Learning from Historical and On-the-Fly Execution Data for Smarter Seed Generation in OS kernel Fuzzing
Boyu Liu, Yang Zhang, Liang Cheng +6
OS Kernel fuzzers such as Syzkaller often struggle to generate syscall sequences that respect intrinsic Syscall Dependency Relations (SDRs), resulting in seeds that either violate…
AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop
Yunfei Teng, Jing Wang, Anna Choromanska
Modern deep learning (DL) architectures are trained using variants of the SGD algorithm that is run with a defined learning rate schedule, i.e., the learning ra…
Quantile Filtered Imitation Learning
David Brandfonbrener, William F. Whitney, Rajesh Ranganath +1
We introduce quantile filtered imitation learning (QFIL), a novel policy improvement operator designed for offline reinforcement learning. QFIL performs policy improvement by runni…
On the Gaussian surface area of spectrahedra
Srinivasan Arunachalam, Oded Regev, Penghui Yao
We show that for sufficiently large and for some universal constant , a random spectrahedron with matrices drawn from Gaussian orthogonal ensemble has…
Constraints on GeV Dark Matter interaction with baryons, from a novel Dewar experiment
Xingchen Xu, Glennys R. Farrar
Dark matter which scatters off ordinary matter with a relatively large cross section cannot be constrained by deep underground WIMP experiments, due to the energy loss of DM along…
A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks
Yefan Zhou, Yiru Shen, Yujun Yan +2
Neural networks (NN) for single-view 3D reconstruction (SVR) have gained in popularity. Recent work points out that for SVR, most cutting-edge NNs have limited performance on recon…