Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Park, Haekyu"'
Autor:
Lee, Seongmin, Hoover, Benjamin, Strobelt, Hendrik, Wang, Zijie J., Peng, ShengYun, Wright, Austin, Li, Kevin, Park, Haekyu, Yang, Haoyang, Chau, Polo
Diffusion-based generative models' impressive ability to create convincing images has garnered global attention. However, their complex internal structures and operations often pose challenges for non-experts to grasp. We introduce Diffusion Explaine
Externí odkaz:
http://arxiv.org/abs/2404.16069
Re-finding information is an essential activity, however, it can be difficult when people struggle to express what they are looking for. Through a need-finding survey, we first seek opportunities for improving re-finding experiences, and explore one
Externí odkaz:
http://arxiv.org/abs/2305.07930
Autor:
Lee, Seongmin, Hoover, Benjamin, Strobelt, Hendrik, Wang, Zijie J., Peng, ShengYun, Wright, Austin, Li, Kevin, Park, Haekyu, Yang, Haoyang, Chau, Duen Horng
Diffusion-based generative models' impressive ability to create convincing images has garnered global attention. However, their complex structures and operations often pose challenges for non-experts to grasp. We present Diffusion Explainer, the firs
Externí odkaz:
http://arxiv.org/abs/2305.03509
Autor:
Zhou, Zhiyan, Li, Kevin, Park, Haekyu, Dass, Megan, Wright, Austin, Das, Nilaksh, Chau, Duen Horng
We present our ongoing work NeuroMapper, an in-browser visualization tool that helps machine learning (ML) developers interpret the evolution of a model during training, providing a new way to monitor the training process and visually discover reason
Externí odkaz:
http://arxiv.org/abs/2210.12492
Autor:
Lee, Seongmin, Afroz, Sadia, Park, Haekyu, Wang, Zijie J., Shaikh, Omar, Sehgal, Vibhor, Peshin, Ankit, Chau, Duen Horng
As the information on the Internet continues growing exponentially, understanding and assessing the reliability of a website is becoming increasingly important. Misinformation has far-ranging repercussions, from sowing mistrust in media to underminin
Externí odkaz:
http://arxiv.org/abs/2210.00160
Autor:
Park, Haekyu, Lee, Seongmin, Hoover, Benjamin, Wright, Austin P., Shaikh, Omar, Duggal, Rahul, Das, Nilaksh, Li, Kevin, Hoffman, Judy, Chau, Duen Horng
We present ConceptEvo, a unified interpretation framework for deep neural networks (DNNs) that reveals the inception and evolution of learned concepts during training. Our work addresses a critical gap in DNN interpretation research, as existing meth
Externí odkaz:
http://arxiv.org/abs/2203.16475
Autor:
Park, Haekyu, Das, Nilaksh, Duggal, Rahul, Wright, Austin P., Shaikh, Omar, Hohman, Fred, Chau, Duen Horng
Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are collectively encoded by multiple neurons. We present NeuroCartography, an
Externí odkaz:
http://arxiv.org/abs/2108.12931
Autor:
Wright, Austin P, Ziems, Caleb, Park, Haekyu, Saad-Falcon, Jon, Chau, Duen Horng, Yang, Diyi, Tomprou, Maria
As job markets worldwide have become more competitive and applicant selection criteria have become more opaque, and different (and sometimes contradictory) information and advice is available for job seekers wishing to progress in their careers, it h
Externí odkaz:
http://arxiv.org/abs/2106.11846
Autor:
Wright, Austin P, Shaikh, Omar, Park, Haekyu, Epperson, Will, Ahmed, Muhammed, Pinel, Stephane, Chau, Duen Horng, Yang, Diyi
With the widespread use of toxic language online, platforms are increasingly using automated systems that leverage advances in natural language processing to automatically flag and remove toxic comments. However, most automated systems -- when detect
Externí odkaz:
http://arxiv.org/abs/2102.04427
Autor:
Park, Haekyu, Wang, Zijie J., Das, Nilaksh, Paul, Anindya S., Perumalla, Pruthvi, Zhou, Zhiyan, Chau, Duen Horng
Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. However, such models are vulnerable to adversarial attacks, raising serio
Externí odkaz:
http://arxiv.org/abs/2101.10586