Nathan Ng

Postdoc at @nyuniversity. PhD @UofT/@MIT.

[PatronusAI @PatronusAI]

1/ Today, we are thrilled to announce Generative Simulators, a new class of adaptive, auto-scaling environments for AGI training and evaluation 🤖🧵

Static datasets, hand-authored environments, and human-curated demonstrations do not automatically scale with the learning patterns of the trained model. We propose Generative Simulators as a principled alternative: environments that evolve, evaluate, and adapt to agent behavior over time.

Technical Report: https://t.co/K79LKSrkoF
Blog: https://t.co/nlI8iBXpsE

[Rebecca Qian @rebeccatqian]

Thrilled to announce our work on Generative Simulation that will enable a new class of adaptive auto-scaling RL environments.

If you’re excited by auto-scaling environments, I’d love to chat!

[Nathan Ng @learn_ng]

@wgrathwohl Sushi Sho and it's not close

[Andrew Ng @andrewng_synbio]

Very proud to share this work from the Advanced Cell Engineering team at Genentech! We developed what we believe to be the best inducible CRISPR system yet that has nearly undetectable levels of leakiness and activation levels that match constitutive expression 🤩

[Nathan Ng @learn_ng]

@cleaming_ Donuts - J Dilla

[Nathan Ng @learn_ng]

@stanislavfort Can't seem to DM you but would love to chat! I'll try email

[Nathan Ng @learn_ng]

I'll be presenting this poster at #ICML2024 tomorrow morning! Stop by and chat about our work!

I'll be around until Thursday, DM me if you'd like to chat about influence functions, uncertainty quantification, or robustness!

[Nathan Ng @learn_ng]

The minimum description length principle is an attractive Bayesian alternative for quantifying uncertainty, but how can we get it to work efficiently and accurately at scale?

Excited to share our ICML work on measuring stochastic complexity with Boltzmann influence functions!

[Nathan Ng @learn_ng]

None of this work would have been possible without guidance from @MarzyehGhassemi and @RogerGrosse to whom I'm extremely grateful. This project took over a year of hard work from its initial conception and capped off the final year of my PhD!

[Nathan Ng @learn_ng]

The minimum description length principle is an attractive Bayesian alternative for quantifying uncertainty, but how can we get it to work efficiently and accurately at scale?

Excited to share our ICML work on measuring stochastic complexity with Boltzmann influence functions!

[Nathan Ng @learn_ng]

Overall this is the paper I'm most proud of during my PhD, and I think there's a lot more interesting insights hidden in the MDL literature.

If you want to read more, check out the
arXiv: https://t.co/6QYek6RHxt
blog post: https://t.co/ndgvEe3geB (should be up soon)