Xiaomin LIN

Prof. Xiaomin LIN

Electrical and Computer Engineering, University of South Florida, Tampa, Florida, USA
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
25 June 2026
Verified
Book Chapter
Closed access
MMMingyang Mao
Mingyang Mao
MPMariela M. Perez-Cabarcas
Mariela M. Perez-Cabarcas
UKUtteja Kallakuri
Utteja Kallakuri
NWNicholas R. Waytowich
Nicholas R. Waytowich
Xiaomin LINXiaomin LIN
Xiaomin LIN
TMTinoosh Mohsenin
Tinoosh Mohsenin

20 April 2026 in Ecological Informatics
Verified
Journal Article
Open access
IDIsla C Duporge
Isla C Duporge
ZWZhenqi Wu
Zhenqi Wu
MBMatthew E. Black
Matthew E. Black
SWScott Wolf
Scott Wolf
AAAngela Albi
Angela Albi
Xiaomin LINXiaomin LIN
Xiaomin LIN

1 January 2007 in MRS Proceedings
Verified
Journal Article
Closed access
PDF file
GNGeorge Nolas
George Nolas
Matt BeekmanMatt Beekman
Matt Beekman
JMJoshua Martin
Joshua Martin
DWDongli Wang
Dongli Wang
Xiaomin LINXiaomin LIN
Xiaomin LIN

24 July 2025 in arXiv
Verified
Preprint
Open access
PDF file
YFYihong Feng
Yihong Feng
CPChaitanya Pallerla
Chaitanya Pallerla
Xiaomin LINXiaomin LIN
Xiaomin LIN
PSPouya Sohrabipour
Pouya Sohrabipour
PCPhil Glen Crandall
Phil Glen Crandall
Dongyi WangDongyi Wang
Dongyi Wang
The poultry industry has been driven by broiler chicken production and has grown into the world's largest animal protein sector. Automated detection of chicken carcasses on processing lines is vital for quality control, food safety, and operational efficiency in slaughterhouses and poultry processing plants. However, developing robust deep learning models for tasks like instance segmentation in these fast-paced industrial environments is often hampered by the need for laborious acquisition and annotation of large-scale real-world image datasets. We present the first pipeline generating photo-realistic, automatically labeled synthetic images of chicken carcasses. We also introduce a new benchmark dataset containing 300 annotated real-world images, curated specifically for poultry segmentation research. Using these datasets, this study investigates the efficacy of synthetic data and automatic data annotation to enhance the instance segmentation of chicken carcasses, particularly when real annotated data from the processing line is scarce. A small real dataset with varying proportions of synthetic images was evaluated in prominent instance segmentation models. Results show that synthetic data significantly boosts segmentation performance for chicken carcasses across all models. This research underscores the value of synthetic data augmentation as a viable and effective strategy to mitigate data scarcity, reduce manual annotation efforts, and advance the development of robust AI-driven automated detection systems for chicken carcasses in the poultry processing industry.


17 March 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
UGUtkarsh Grover
Utkarsh Grover
Ravi RanjanRavi Ranjan
Ravi Ranjan
MMMingyang Mao
Mingyang Mao
TDTrung Tien Dong
Trung Tien Dong
SPSatvik Praveen
Satvik Praveen
Xiaomin LINXiaomin LIN
Xiaomin LIN
Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size, weight, and power constraints, where memory traffic, compute latency, timing variability, and safety margins interact directly. The Deployment Gauntlet organizes these constraints into eight coupled barriers that determine whether embodied foundation models can run reliably in practice. Across representative edge workloads, autoregressive Vision-Language-Action policies are constrained primarily by memory bandwidth, whereas diffusion-based controllers are limited more by compute latency and sustained execution cost. Reliable deployment therefore depends on system-level co-design across memory, scheduling, communication, and model architecture, including decompositions that separate fast control from slower semantic reasoning.