Search Results for author:
Found 11 papers, 5 papers with code
Context-dependent Instruction Tuning for Dialogue Response Generation
Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning.
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
Previous DaNAS methods have mostly tackled the search for the neural architecture for fixed datasets and the teacher, which are not generalized well on a new task consisting of an unseen dataset and an unseen teacher, thus need to perform a costly search for any new combination of the datasets and the teachers.
Prediction of Protein Aggregation Propensity via Data-driven Approaches
Protein aggregation occurs when misfolded or unfolded proteins physically bind together, and can promote the development of various amyloid diseases.
Language Detoxification with Attribute-Discriminative Latent Space
Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world applications.
Learning Transferable Adversarial Robust Representations via Multi-view Consistency
Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples.
Design of a novel Korean learning application for efficient pronunciation correction
The Korean wave, which denotes the global popularity of South Korea's cultural economy, contributes to the increasing demand for the Korean language.
Machine Learning-Aided Discovery of Superionic Solid-State Electrolyte for Li-Ion Batteries
In this study, a platform consisting of a high-throughput screening and a machine-learning surrogate model for discovering superionic Li-SSEs among 20, 237 Li-containing materials is developed.
Entropy Weighted Adversarial Training
Adversarial training methods, which minimizes the loss of adversarially-perturbed training examples, have been extensively studied as a solution to improve the robustness of the deep neural networks.
Consistency Regularization for Adversarial Robustness
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks.
Adversarial Self-Supervised Contrastive Learning
In this paper, we propose a novel adversarial attack for unlabeled data, which makes the model confuse the instance-level identities of the perturbed data samples.
Progressive Face Super-Resolution via Attention to Facial Landmark
Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images.
Ranked #1 on
Face Alignment
on CelebA + AFLW Unaligned
