Zobrazeno 1 - 10
of 261
pro vyhledávání: '"Chau, Duen Horng"'
Autor:
Cho, Aeree, Kim, Grace C., Karpekov, Alexander, Helbling, Alec, Wang, Zijie J., Lee, Seongmin, Hoover, Benjamin, Chau, Duen Horng
Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our t
Externí odkaz:
http://arxiv.org/abs/2408.04619
Autor:
Mehta, Pratham, Narayanan, Rahul O, Karanth, Harsha, Yang, Haoyang, Slesnick, Timothy C, Shaw, Fawwaz, Chau, Duen Horng
Collaborative planning for congenital heart diseases typically involves creating physical heart models through 3D printing, which are then examined by both surgeons and cardiologists. Recent developments in mobile augmented reality (AR) technologies
Externí odkaz:
http://arxiv.org/abs/2408.03249
Autor:
Wang, Zijie J., Chau, Duen Horng
Retrieval-augmented text generation (RAG) addresses the common limitations of large language models (LLMs), such as hallucination, by retrieving information from an updatable external knowledge base. However, existing approaches often require dedicat
Externí odkaz:
http://arxiv.org/abs/2407.01972
Safety alignment is the key to guiding the behaviors of large language models (LLMs) that are in line with human preferences and restrict harmful behaviors at inference time, but recent studies show that it can be easily compromised by finetuning wit
Externí odkaz:
http://arxiv.org/abs/2405.17374
Autor:
Lee, Seongmin, Wang, Zijie J., Chakravarthy, Aishwarya, Helbling, Alec, Peng, ShengYun, Phute, Mansi, Chau, Duen Horng, Kahng, Minsuk
While large language models (LLMs) have shown remarkable capability to generate convincing text across diverse domains, concerns around its potential risks have highlighted the importance of understanding the rationale behind text generation. We pres
Externí odkaz:
http://arxiv.org/abs/2404.01361
Autor:
Peng, ShengYun, Chakravarthy, Aishwarya, Lee, Seongmin, Wang, Xiaojing, Balasubramaniyan, Rajarajeswari, Chau, Duen Horng
Tables convey factual and quantitative data with implicit conventions created by humans that are often challenging for machines to parse. Prior work on table recognition (TR) has mainly centered around complex task-specific combinations of available
Externí odkaz:
http://arxiv.org/abs/2403.04822
Autor:
Peng, ShengYun, Lee, Seongmin, Wang, Xiaojing, Balasubramaniyan, Rajarajeswari, Chau, Duen Horng
Table structure recognition (TSR) aims to convert tabular images into a machine-readable format. Although hybrid convolutional neural network (CNN)-transformer architecture is widely used in existing approaches, linear projection transformer has outp
Externí odkaz:
http://arxiv.org/abs/2402.15578
Autor:
Mehta, Pratham, Karanth, Harsha, Yang, Haoyang, Slesnick, Timothy, Shaw, Fawwaz, Chau, Duen Horng
Surgical planning for congenital heart diseases requires a collaborative approach, traditionally involving the 3D-printing of physical heart models for inspection by surgeons and cardiologists. Recent advancements in mobile augmented reality (AR) tec
Externí odkaz:
http://arxiv.org/abs/2402.05075
Autor:
Blalock, Justin, Munechika, David, Karanth, Harsha, Helbling, Alec, Mehta, Pratham, Lee, Seongmin, Chau, Duen Horng
The growing digital landscape of fashion e-commerce calls for interactive and user-friendly interfaces for virtually trying on clothes. Traditional try-on methods grapple with challenges in adapting to diverse backgrounds, poses, and subjects. While
Externí odkaz:
http://arxiv.org/abs/2402.01877
Large language models (LLMs) require well-crafted prompts for effective use. Prompt engineering, the process of designing prompts, is challenging, particularly for non-experts who are less familiar with AI technologies. While researchers have propose
Externí odkaz:
http://arxiv.org/abs/2401.14447