Industry
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks Zhaohan Xi
In this work, we conduct a pilot study showing that PLMs as few-shot learners are highly vulnerable to backdoor attacks while existing defenses are inadequate due to the unique challenges of few-shot scenarios.
Block Coordinate Regularization by Denoising
Yu Sun, Jiaming Liu, Ulugbek Kamilov
Neural Information Processing Systems http://nips.cc/
ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
Andrei Barbu, David Mayo, Julian Alverio, William Luo, Christopher Wang, Dan Gutfreund, Josh Tenenbaum, Boris Katz
ObjectNet is the same size as the ImageNet test set (50,000 images), and by design does not comepaired withatraining setinordertoencourage generalization.
Neural Ordinary Differential Equations
Tian Qi Chen, Yulia Rubanova, Jesse Bettencourt, David K. Duvenaud
Neural Information Processing Systems http://nips.cc/
cell
However,theanalysis ofsuchdataposes challenges due to the high levels of noise, sparsity, and data scale encountered.
Private Hypothesis Selection
Mark Bun, Gautam Kamath, Thomas Steinke, Steven Z. Wu
We provide a differentially private algorithm for hypothesis selection.
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
Ye Jia, Yu Zhang, Ron Weiss, Quan Wang, Jonathan Shen, Fei Ren, zhifeng Chen, Patrick Nguyen, Ruoming Pang, Ignacio Lopez Moreno, Yonghui Wu
Neural Information Processing Systems http://nips.cc/