10.9k citations
- University of MichiganUS43 papers
- Massachusetts Institute of TechnologyUS42 papers
- University of Illinois Urbana-ChampaignUS42 papers
- Joint Institute for Nuclear ResearchRU41 papers
- University of PennsylvaniaUS41 papers
- Michigan State UniversityUS40 papers
- University of New MexicoUS40 papers
- University of TsukubaJP40 papers
- University of Wisconsin–MadisonUS40 papers
- Waseda UniversityJP40 papers
- National and Kapodistrian University of AthensGR39 papers
- Philadelphia UniversityUS39 papers
37 papers · 1 filter
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction
Jhih-Wei Chen, Tsu-Jui Fu, Chen-Kang Lee +1
Although distant supervision automatically generates training data for relation extraction, it also introduces false-positive (FP) and false-negative (FN) training instances to the…
Deterministic Certification to Adversarial Attacks via Bernstein Polynomial Approximation
Ching-Chia Kao, Jhe-Bang Ko, Chun-Shien Lu
Randomized smoothing has established state-of-the-art provable robustness against norm adversarial attacks with high probability. However, the introduced Gaussian data aug…
Predicted septuple-atomic-layer Janus (M=Mo and W) monolayers with Rashba spin splitting and high electron carrier mobilities
San-Dong Guo, Wen-Qi Mu, Yu-Tong Zhu +2
Janus two-dimensional (2D) materials have attracted much attention due to possessing unique properties caused by their out-of-plane asymmetry, which have been achieved in many 2D f…
A novel quad-channel 10 Gbps CMOS VCSEL array driver with integrated charge pumps
X. Huang, D. Gong, D. Guo +14
We present a novel design and the test results of a 4-channel driver for an array of Vertical-Cavity Surface-Emitting Lasers (VCSELs). This ASIC, named cpVLAD and fabricated in a 6…
A 20 Gbps Data Transmitting ASIC with PAM4 for Particle Physics Experiments
Li Zhang, Datao Gong, Suen Hou +9
We present the design principle and test results of a data transmitting ASIC, GBS20, for particle physics experiments. The goal of GBS20 will be an ASIC that employs two serializer…
TinyGAN: Distilling BigGAN for Conditional Image Generation
Ting-Yun Chang, Chi-Jen Lu
Generative Adversarial Networks (GANs) have become a powerful approach for generative image modeling. However, GANs are notorious for their training instability, especially on larg…