Sign in

Sergei V. Kalinin

@sergei-imaging.bsky.social
878 followers 709 following 40 posts

I like using machine learning to solve problems in physics, from discovering physical laws from observational microscopy data, designing and making better materials, and moving atoms by electron beams. Currently my group build automated microscopes.

PostsRepliesMedia
Sergei V. Kalinin @sergei-imaging.bsky.social · 25/07/2025
Тяжела ты, шапка Мономаха...
010
Sergei V. Kalinin @sergei-imaging.bsky.social · 09/07/2025
!pip install
000
Sergei V. Kalinin @sergei-imaging.bsky.social · 01/07/2025
After talking to several of my senior colleagues in academia, I somehow remember the most famous tanka by Ono no Komachi....
000
Sergei V. Kalinin @sergei-imaging.bsky.social · 24/04/2025
AI comedy night - exploring career pivot to stand up comedy www.youtube.com/watch?v=jNP7...
youtube.com
Sergei Kalinin, MicNite Spring 2025
YouTube video by MicNite UTK
010
Sergei V. Kalinin @sergei-imaging.bsky.social · 17/03/2025
🙏 Off to the APS March meeting to give Adler Prize lecture on closing the characterization loop via reward driven workflows. DM if you would like to meet and grab a coffee! What makes this conference special is that it is also the first talk of Dmitri Kalinin!
040
Sergei V. Kalinin @sergei-imaging.bsky.social · 23/02/2025
My belief in humanity is restored
030
Sergei V. Kalinin @sergei-imaging.bsky.social · 04/02/2025
Automated STEM in action. So many particles, so little time... But now AE STEM can do it www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: 🚀 So many particles, so little time to study plasmonic effects .... Not…
🚀 So many particles, so little time to study plasmonic effects .... Not anymore - see automated STEM operationalized by Austin Houston and Utkarsh Pratiush…
050
Sergei V. Kalinin @sergei-imaging.bsky.social · 28/01/2025
Pro tip - if you have to wake up at night a lot to take care of baby, luminescent tape on all edges minimizes probability of toe damage
140
Sergei V. Kalinin @sergei-imaging.bsky.social · 15/01/2025
Newcomer to automated experiment world - ML-enabled nanoindentation www.linkedin.com/posts/activi...
linkedin.com
Sign Up | LinkedIn
500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.
040
Sergei V. Kalinin @sergei-imaging.bsky.social · 15/01/2025
Ferrofluid and Frank Sinatra. It doesn't get better.
020
Sergei V. Kalinin @sergei-imaging.bsky.social · 11/01/2025
A question to my colleagues in computer vision - what is the best way to identify objects and data variability in Esher drawings?
020
Sergei V. Kalinin @sergei-imaging.bsky.social · 30/12/2024
Dune Prophecy made Dune very small
110
Sergei V. Kalinin @sergei-imaging.bsky.social · 26/12/2024
Python is successfully installed, but now no mouse is detected....
060
Sergei V. Kalinin @sergei-imaging.bsky.social · 25/12/2024
Russo - Iranian XMas. Vodka is from Texas.
160
Sergei V. Kalinin @sergei-imaging.bsky.social · 25/12/2024
شب یالدا
060
Sergei V. Kalinin @sergei-imaging.bsky.social · 20/12/2024
Welcome to Knoxville, Vasily Kalinin!
040
Sergei V. Kalinin @sergei-imaging.bsky.social · 19/12/2024
Asking for advice from molecular discovery and ML community re practical databases - will appreciate leads! www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: 🌟 Seeking Advice from the Molecular Discovery Community 🌟 Recently, our…
🌟 Seeking Advice from the Molecular Discovery Community 🌟 Recently, our team have experimented with some simple molecular discovery algorithms. However, for…
030
Sergei V. Kalinin @sergei-imaging.bsky.social · 16/12/2024
Showing the automated labs in University of Tennessee Tickle College of Engineering to Steven Spurgeon . The Spectra 300 with HPC control, Jupiter AFM, and the fleet of pipetting robots and SpinBot at Mahshid Ahmadi lab. It works, and it works together!
020
Sergei V. Kalinin @sergei-imaging.bsky.social · 16/12/2024
Machine learning and AI can help only those who know how to help themselves
050
Sergei V. Kalinin @sergei-imaging.bsky.social · 16/12/2024
Hackaton launch! www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: 🔬 🪄 Hackathon launch! Happy to welcome everyone to the launch of the…
🔬 🪄 Hackathon launch! Happy to welcome everyone to the launch of the ML/AI for the Microscopy Hackathon! Starting with the intro talks by Gerd Duscher…
010
Sergei V. Kalinin @sergei-imaging.bsky.social · 11/12/2024
SVK -> Fellow, National Academy of Inventors research.utk.edu/oried/2024/1...
research.utk.edu
Kalinin, Melcher Named NAI Fellows - Research, Innovation & Economic Development
University of Tennessee Knoxville professors Sergei Kalinin and Chuck Melcher have been named NAI Fellows.
010
Sergei V. Kalinin @sergei-imaging.bsky.social · 02/12/2024
Reinforcement learning is not the right algorithm for the cartpole problem. LLMs are not the right algorithm for math or causal inference. It's amazing to see the ML community trying to use fantastic tools for tasks they are not built for.
060
Sergei V. Kalinin @sergei-imaging.bsky.social · 01/12/2024
With a defined reward function, everything is an optimization problem. And we know how to solve optimization problems.
030
Sergei V. Kalinin @sergei-imaging.bsky.social · 30/11/2024
If you plan to attend MRS in Boston - will be happy to connect! www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: 🧱 🍁 Fall MRS in Boston - if you plan to attend, drop me a note to…
🧱 🍁 Fall MRS in Boston - if you plan to attend, drop me a note to connect in person and you are welcome to the talks and posters from my and Mahshid Ahmadi…
170
Sergei V. Kalinin @sergei-imaging.bsky.social · 29/11/2024
Intro to Machine Learning for Materials Science: from ontologies and NLP to causality and decision making www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: GitHub - SergeiVKalinin/MSE_Fall2024
🎓 Reflecting on "Introduction to Machine Learning for Materials Science"🎓 As the semester comes to a close, it’s a great time to look back on the second…
0283
Sergei V. Kalinin @sergei-imaging.bsky.social · 28/11/2024
Sproggy guards the turkey
020
Sergei V. Kalinin @sergei-imaging.bsky.social · 27/11/2024
How important is quantum mechanics for materials science? www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: Prof. M.I. Katsnelson (Mikhail) | Radboud University
✨ How important is quantum mechanics for materials science? A very interesting opinion by Mikhail Katsnelson (translated from Russian and slightly abridged in…
030
Sergei V. Kalinin @sergei-imaging.bsky.social · 27/11/2024
So Microsoft now can datamine all Word and PowerPoint docs as we type them unless opt out? www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: No matter how long I have been using Word and PowerPoint, it starts to…
No matter how long I have been using Word and PowerPoint, it starts to feel like time to switch to Overleaf, Unix, etc. Given how vulnerable are LLMs for…
100
Sergei V. Kalinin @sergei-imaging.bsky.social · 25/11/2024
It's a very special feeling when you are 5 minutes over time in class, and the students look at you expecting the lecture to continue.
120
Sergei V. Kalinin @sergei-imaging.bsky.social · 23/11/2024
AI/ML for scanning probe microscope - use digital twin to transition from in silico to in materio! www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: GitHub - RichardLiuCoding/spmsimu: Scanning Probe Microscopy Simulator…
🧙‍♂️ Build your own digital twin of scanning probe microscope It is difficult to make ML/AI real - simply because whereas in silico we can do anything…
040
Sergei V. Kalinin @sergei-imaging.bsky.social · 22/11/2024
For the last 20 years, we were scaling theory. For the last 5, synthesis. It's time for characterization and feedback to theory. Which also means that we need light models that can be updated based on individual experiments, and ways to integrate them into more universal ones.
130
Sergei V. Kalinin @sergei-imaging.bsky.social · 20/11/2024
And reward based workflows for image analysis: unsupervised, explainable, robust, and allowing for human in the loop tuning. arxiv.org/abs/2411.12612
arxiv.org
Reward driven workflows for unsupervised explainable analysis of phases and ferroic variants from atomically resolved imaging data
Rapid progress in aberration corrected electron microscopy necessitates development of robust methods for the identification of phases, ferroic variants, and other pertinent aspects of materials struc...
000
Sergei V. Kalinin @sergei-imaging.bsky.social · 20/11/2024
Reward based microscopy optimization - how to make things work better when there is no training data, but we can build human heuristics or physics based reward function arxiv.org/abs/2411.12065
arxiv.org
Reward based optimization of resonance-enhanced piezoresponse spectroscopy
Dynamic spectroscopies in Scanning Probe Microscopy (SPM) are critical for probing material properties, such as force interactions, mechanical properties, polarization switching, and electrochemical r...
020
Sergei V. Kalinin @sergei-imaging.bsky.social · 17/11/2024
Join the microscopy hackaton (and see the actual video of the hacker infiltrating the microscope room) www.linkedin.com/posts/sergei...
linkedin.com
Sergei Kalinin on LinkedIn: #microscopy #hackathon #innovation #ai #machinelearning #stem…
🎥 Microscope Hackers Unite! 🔬💻 Ever thought about hacking a microscope? 🔍 In our latest promo video, a daring hacker Austin Houston tries to break into…
050
Reposted by Sergei V. Kalinin
Volker Blum @aimsduke.bsky.social · 16/11/2024
I know everyone else noticed too, but I'm still amazed, happy and unexpectedly distracted by the old chemtwitter suddenly re-forming on chemsky. Made my week so much better and I hope it'll make everyone else's life better, too. Great to see everyone here.
211411