1 code implementation • Findings (ACL) 2022 • KiYoon Yoo, Jangho Kim, Jiho Jang, Nojun Kwak
Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years.
no code implementations • 28 Mar 2024 • Namhyuk Ahn, Wonhyuk Ahn, KiYoon Yoo, Daesik Kim, Seung-Hun Nam
Recent progress in diffusion models has profoundly enhanced the fidelity of image generation.
no code implementations • 8 Dec 2023 • Inseop Chung, KiYoon Yoo, Nojun Kwak
To handle this task, the model has to learn a generalizable representation that can be applied to unseen domains while also identify unknown classes that were not present during training.
1 code implementation • 1 Aug 2023 • KiYoon Yoo, Wonhyuk Ahn, Nojun Kwak
By independently embedding sub-units of messages, the proposed method outperforms the existing works in terms of robustness and latency.
1 code implementation • 3 May 2023 • KiYoon Yoo, Wonhyuk Ahn, Jiho Jang, Nojun Kwak
Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models.
no code implementations • 29 Apr 2022 • KiYoon Yoo, Nojun Kwak
For a less complex dataset, a mere 0. 1% of adversary clients is enough to poison the global model effectively.
no code implementations • 3 Mar 2022 • KiYoon Yoo, Jangho Kim, Jiho Jang, Nojun Kwak
Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years.
1 code implementation • 25 Nov 2021 • Jiho Jang, Seonhoon Kim, KiYoon Yoo, Chaerin Kong, Jangho Kim, Nojun Kwak
Through self-distillation, the intermediate layers are better suited for instance discrimination, making the performance of an early-exited sub-network not much degraded from that of the full network.
no code implementations • 7 Oct 2021 • Simyung Chang, KiYoon Yoo, Jiho Jang, Nojun Kwak
Utilizing SEO for PFL, we also introduce self-evolutionary Pareto networks (SEPNet), enabling the unified model to approximate the entire Pareto front set that maximizes the hypervolume.
1 code implementation • 10 Sep 2021 • Jangho Kim, Jayeon Yoo, Yeji Song, KiYoon Yoo, Nojun Kwak
To alleviate this problem, dynamic pruning methods have emerged, which try to find diverse sparsity patterns during training by utilizing Straight-Through-Estimator (STE) to approximate gradients of pruned weights.
no code implementations • 20 Oct 2020 • Sangho Lee, KiYoon Yoo, Nojun Kwak
Federated learning (FL), which utilizes communication between the server (core) and local devices (edges) to indirectly learn from more data, is an emerging field in deep learning research.
no code implementations • 9 Sep 2020 • SeongUk Park, KiYoon Yoo, Nojun Kwak
In this paper, we focus on knowledge distillation and demonstrate that knowledge distillation methods are orthogonal to other efficiency-enhancing methods both analytically and empirically.
1 code implementation • NeurIPS 2020 • Jangho Kim, KiYoon Yoo, Nojun Kwak
Second, we empirically show that PSG acting as a regularizer to a weight vector is favorable for model compression domains such as quantization and pruning.