Skip to content
View samholt's full-sized avatar
💭
Building the future
💭
Building the future

Highlights

  • Pro

Block or report samholt

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
samholt/README.md

I was a recent RS intern at Google DeepMind, and I am a fourth-year Ph.D. student in Machine Learning at the University of Cambridge advised by Mihaela van der Schaar in the Machine Learning and Artificial Intelligence group. To date, I have published nine papers as first or joint first author in top-tier ML conferences (NeurIPS [spotlight], ICML [long oral], ICLR [spotlight] and AISTATS).

I thrive driving foundational research to advance the state-of-the-art for LLM output generation, including LLM agents using external memory and tool use. My recent work solved key problems to enable LLM agents for generating coherent outputs at scale, beyond context limits through updating external memory and multi-agent generation evolutionary frameworks. I would love to be part of a team to invent and drive new prototypes forwards by adapting flexibly to deliver project success in the areas of multi-modal LLM agents, and using RL to improve LLM agents automatically. Here on GitHub you can find research projects as well as open source software developed in my spare time.

Pinned Loading

  1. L2MAC L2MAC Public

    🚀 The LLM Automatic Computer Framework: L2MAC

    Python 107 30

  2. NeuralLaplace NeuralLaplace Public

    Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.

    Python 75 12

  3. PacktPublishing/Practical-Machine-Learning-with-TensorFlow-2.0-and-Scikit-Learn PacktPublishing/Practical-Machine-Learning-with-TensorFlow-2.0-and-Scikit-Learn Public

    Practical Machine Learning with TensorFlow 2.0 and Scikit-Learn [Video], published by Packt

    Jupyter Notebook 56 25