Robust Text Perturbation using Sequence-to-Sequence Pre-Training
- Nishtha Madaan
- Diptikalyan Saha
- et al.
- 2021
- NeurIPS 2021
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
675 results for Trustworthy AI
Detecting model drift using polynomial relations
- Eliran Roffe
- Samuel Ackerman
- et al.
- 2022
- AAAI 2022
Simple Transparent Adversarial Examples
- Jaydeep Borkar
- Pin-Yu Chen
- 2021
- ICLR 2021
Fairly Estimating Socioeconomic Status Under Costly Feature Acquisition
- Ritika Brahmadesam
- Kush R. Varshney
- 2021
- ICLR 2021
Towards an Observationally Meaningful, Explainable Emulator for the Boussinesq equation
- 2021
- ICLR 2021
Adversarial Data Augmentation Improves Unsupervised Machine Learning
- Chia-Yi Hsu
- Pin-Yu Chen
- et al.
- 2021
- ICLR 2021
High-Robustness, Low-Transferability Fingerprinting of Neural Networks
- Siyue Wang
- Xiao Wang
- et al.
- 2021
- ICLR 2021
Causal Inference Q-Network: Toward Resilient Reinforcement Learning
- Huck Yang
- I-Te Hung
- et al.
- 2021
- ICLR 2021
Toward Non-Singular Robustness of Neural Networks
- Yu-Lin Tsai
- Chia-Yi Hsu
- et al.
- 2021
- ICLR 2021
Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations
- Yu-Lin Tsai
- Chia-Yi Hsu
- et al.
- 2021
- ICLR 2021