Published on

Research from NeurIPS


Sam Witteveen and I started the Machine Learning Singapore Group (or MLSG for short) on MeetUp in February 2017 (it was previously named "TensorFlow and Deep Learning Singapore"), and the forty-ninth MeetUp was our thirteenth 'in-person' event since the COVID era.

The overall event was our "Annual NeurIPS Recap", and my talk "Eye-catching Research from NeurIPS" - reflecting my take-aways from attending NeurIPS (virtually) in December 2023:

  • Maths stuff (Tutorial & Workshop)
    • Reasoning in AI / LLMs
    • What are provers?
    • LLMs for Maths
    • Breaking News : AlphaGeometry
  • Other stuff :
    • Paper Déjà Vu
    • Tool Use; LLM Reasoning; and Small Models
    • Evolution Ideas
    • Odd-Ball Idea Prize :
      • Multiplication-Free Transformer Training via Piecewise Affine Operations

Sam talked about the LLM sessions at NeurIPS (Papers, Workshops and Panel Discussions), and also discussed recent developments in the LLM world extensively.

We also were pleased to have Sheila Teo giving a talk on how she won Singapore GovTech's Prompt Engineering Competition, including:

  • Strategies for Winning prompts; and
  • How to innovate in the prompting space

Many thanks to the Google team, who not only allowed us to use Google's Developer Space, and put out the extra chairs required for our larger-than-expected attendence, but were also kind enough to provide Pizza for the attendees!

The slides for my talk, which contain links to all of the reference materials and sources, are here :

Presentation Screenshot

If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.

Presentation Content Example