Yupeng Cao

Mr. Yupeng Cao

Stevens Institute of Technology, Hoboken, New Jersey, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
14 October 2022 in Foods
Verified
Journal Article
Open access
PDF file
WLWenbo Liu
Wenbo Liu
JLJiaqi Lyu
Jiaqi Lyu
DWDi Wu
Di Wu
YCYupeng Cao
Yupeng Cao
QMQingquan Ma
Qingquan Ma
Xin ZhangXin Zhang
Xin Zhang
Fish and fishery products are among the most important sources of nutritional components for human health, including high-quality proteins, essential vitamins, minerals, and healthy polyunsaturated fatty acids. Fish farming and processing technologies are continuously evolving to improve and enhance the appearance, yield, and quality of fish and fish products from farm to fork throughout the fish supply chain, including growth, postharvest, treatment, storage, transportation, and distribution. Processing of fish involves a period of food withdrawal, collection and transportation, the process of stunning, bleeding, chilling, cutting, packaging, and byproduct recycling. Cutting is a set of crucial operations in fish processing to divide the whole fish into smaller pieces for producing fish products (e.g., fish fillets, steaks, etc.). Various techniques and machinery have been introduced in the field to advance and automate cutting operations. This review aims to provide a comprehensive review of fish cutting techniques, machine vision and artificial intelligence applications, and future directions in fish industries. This paper is expected to stimulate research on enhancing fish cutting yield, product diversity, safety and quality, as well as providing advanced solutions for engineering problems encountered in the fish industry.
1

23 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
WCWuxinlin Cheng
Wuxinlin Cheng
YCYupeng Cao
Yupeng Cao
JWJinwen Wu
Jinwen Wu
KSKoduvayur Subbalakshmi
Koduvayur Subbalakshmi
THTian Han
Tian Han
ZFZhuo Feng
Zhuo Feng
Recent strides in pretrained transformer-based language models have propelled state-of-the-art performance in numerous NLP tasks. Yet, as these models grow in size and deployment, their robustness under input perturbations becomes an increasingly urgent question. Existing robustness methods often diverge between small-parameter and large-scale models (LLMs), and they typically rely on labor-intensive, sample-specific adversarial designs. In this paper, we propose a unified, local (sample-level) robustness framework (SALMAN) that evaluates model stability without modifying internal parameters or resorting to complex perturbation heuristics. Central to our approach is a novel Distance Mapping Distortion (DMD) measure, which ranks each sample's susceptibility by comparing input-to-output distance mappings in a near-linear complexity manner. By demonstrating significant gains in attack efficiency and robust training, we position our framework as a practical, model-agnostic tool for advancing the reliability of transformer-based NLP systems.