Benjamin Yao

Benjamin Yao

Auto-generated profile, based on publicly available information

Benjamin Yao

Amazon.com, Seattle, WA, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 August 2024
Verified
Conference Paper
Open access
XZXinliang Zhu
Xinliang Zhu
SHSheng-Wei Huang
Sheng-Wei Huang
HDHan Ding
Han Ding
JYJinyu Yang
Jinyu Yang
KCKelvin Chen
Kelvin Chen
ADArnab Dhua
Arnab Dhua
Image to image matching has been well studied in the computer vision community. Previous studies mainly focus on training a deep metric learning model matching visual patterns between the query image and gallery images. In this study, we show that pure image-to- image matching suffers from false positives caused by matching to local visual patterns. To alleviate this issue, we propose to leverage recent advances in vision-language pretraining research. Specifically, we introduce additional image-text alignment losses into deep metric learning, which serve as constraints to the image-to-image matching loss. With additional alignments between the text (e.g., product title) and image pairs, the model can learn concepts from both modalities explicitly, which avoids matching low-level visual features. We progressively develop two variants, a 3-tower and a 4-tower model, where the latter takes one more short text query input. Through extensive experiments, we show that this change leads to a substantial improvement to the image to image matching problem. We further leveraged this model for multimodal search, which takes both image and reformulation text queries to improve search quality. Both offline and online experiments show strong improvements on the main metrics. Specifically, we see 4.95% relative improvement on image matching click through rate with the 3-tower model and 1.13% further improvement from the 4-tower model.

5 April 2024 in IEEE Computational Intelligence Magazine
Verified
Journal Article
Closed access
XLXiaohu Liu
Xiaohu Liu
CGChenlei Guo
Chenlei Guo
BYBenjamin Yao
Benjamin Yao
RSRuhi Sarikaya
Ruhi Sarikaya
In the last decade, conversational artificial intelligence (AI) systems have been widely employed to address people’s real-life needs across various different environments and settings. At the same time, users’ expectations of these systems have been on the rise as they expect more contextual and personalized interactions with continuous learning systems, akin to their expectation in human-human interactions. Modular systems constructed as pipelines of machine learning models and trained through supervised learning paradigms often struggle to improve user experience due to the less-than-ideal, slow accuracy improvements they undergo, and the privacy concerns associated with manual annotation. Inspired by how humans learn from their experiences and interactions, this article proposes a comprehensive self-learning framework designed to tackle these challenges for large-scale conversational AI systems, fostering continuous automated learning. The proposed self-learning framework comprises three elements: feedback collection, feedback interpretation, and learning mechanisms. Without the need for annotators in the loop, a self-learning conversational AI system autonomously uses a feedback interpreter to subscribe to, interpret, and utilize user feedback to adapt its behaviors through various learning mechanisms. First, the elements of the self-learning framework are described and then applied to Alexa, a large-scale conversational AI system. Subsequently, this article presents its effectiveness in reducing user-perceived defects. Finally, it explores the implications of self-learning for general AI systems and suggests future directions.

27 June 2024 in Oriental Journal of Chemistry
Verified
Journal Article
Open access
PDF file
AKAdjoumani Rodrigue Kouakou
Adjoumani Rodrigue Kouakou
MKMarc Cyril Kouadio
Marc Cyril Kouadio
VKVictorien Kouakou
Victorien Kouakou
GKGbangbo Remi Konan
Gbangbo Remi Konan
AEAhissan Donatien Ehouman
Ahissan Donatien Ehouman
BYBenjamin Yao
Benjamin Yao
The objective of this study is to investigate the potential reduction in corrosion of aluminum and copper metals when exposed to biogas purified by activated carbon derived from cashew branches. Both aluminum and copper metals were subjected to raw and purified biogas, and their corrosion rates were analyzed using the gravimetric method. The results revealed that the corrosion rate of both metals increased over time when exposed to unfiltered biogas. However, a notable reduction in corrosion rate was observed when the metals were exposed to biogas filtered with activated carbon. This suggests that activated carbon derived from cashew branches could effectively mitigate the corrosive effects of hydrogen sulfide in biogas. Additionally, the study found that aluminum exhibited greater resistance to corrosion compared to copper when exposed to filtered biogas. This research on green inhibitors introduces novel approaches, particularly in utilizing activated carbon from cashew branches for biogas purification, offering a promising strategy to mitigate its corrosive nature. Furthermore, the evaluation of this filtration method's efficacy in protecting aluminum and copper metals underscores its potential significance in corrosion prevention within biogas systems.