Vaisakh Shaj

Welcome to my personal website. I am a Postdoctoral Researcher in AI and Machine Learning at the University Of Edinburgh working with Prof Amos Storkey. I am affiliated with the Institute Of Adaptive and Neural Computation, School Of Informatics.

I did my PhD in Machine Learning For Control under Prof Gerhard Neumann at the ALR Lab, Karlsruhe Institute Of Technology. Before that I was a Data Scientist at the cybersecurity firm McAfee (Intel Security). Previously I worked with Intel for 2 years. I hold a post graduate degree in Machine Learning and Computing from the Indian Institute of Space Science and Technology.

My doctoral thesis focussed on building “World models With Hierarchical Temporal Abstractions” based on probabilistic and Bayesian principles.

Research

My research interests and expertise lie at the intersection of Deep Learning, Probabilistic Modelling, and Control Theory. My current goal is to build scalable neural network models grounded in probabilistic and control theoretic principles. Currently, my application focus is on building efficient, controllable, and safe large language models (LLMs) and intelligent agents.

Other research directions that I have explored and am still curious about include Hierarchical Modelling, Long Horizon Reasoning/Control, and Learning under Non-Stationarity (Meta/Continual Learning etc).

🌈Diversity and Inclusion Statement: I care deeply about making work places more diverse and the inclusion of women, LGBTQ+ and under-represented minorities in AI research.