2024
Investigated offline preference data selection methods to choose the most helpful preference pairs for model reward tuning with distribution entropy estimates obtained from Stein Variational Gradient Descent (SVGD).
2023
Investigated pretraining methods for a multimodal LLM utilizing emergent communication corpora.
2022
Compare emergent communication between two agents using 1D and 2D paradigms.
2018
This project concerns the simulation of skeletal muscle fiber growth.
Published in International Conference on Automation, Robotics and Applications, 2021
This paper investigates a new method for the assembly of global patterns in a multi-robot swarm following basic mean-shift based formation rules.
Recommended citation: C. Vickery, S.A. Salehi. "A Mean Shift-Based Pattern Formation Algorithm for Robot Swarms," 2021 International Conference on Automation, Robotics and Applications. February 2021. https://ieeexplore.ieee.org/document/9376415
Published in Journal of Applied Physiology, 2018
This paper introduces a new method to run automated image segementation and analysis of skeletal muscle cross-sections combining filtering, binarization, and watershed segmentation techniques.
Recommended citation: Wen Y, Murach KA, Vechetti IJ Jr, et al. MyoVision: software for automated high-content analysis of skeletal muscle immunohistochemistry. J Appl Physiol (1985). 2018;124(1):40–51. doi:10.1152/japplphysiol.00762.2017 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6048460/