Andrew Wang

Machine Learning Graduate Student at @UofTCompSci/@VectorInst advised by @SheilaMcIlraith and @RogerGrosse

[Andrew Wang @andrew_wang10]

Our paper on influence functions titled Better TDA via Better Inverse Hessian-Vector Products will be presented at #neurips25 San Diego on Friday from 4:30 PM - 7:30 PM in Exhibit hall C,D,E (Poster 3907) Work with my fantastic colleagues @_elinguyen, @Runshi_Yang , @juhan_bae, @SheilaMcIlraith, @RogerGrosse!

[Keiran Paster @keirp1]

Proud to introduce Llemma, the first models trained on OpenWebMath (part of the 55B mathematical tokens in ProofPile II).

Llemma serves as a platform for future research on quantitative reasoning and is a very powerful base model for mathematical tasks!

[Yangjun Ruan @YangjunR]

Should you let LMs control your email? terminal? bank account? or even your smart home?🤔

🔥Introducing ToolEmu for identifying risks associated with LM agents at scale!

🛠️Featuring LM-emulation of tools & automated realistic risk detection

🚨GPT4 is risky in 40% of our cases!

[Aran Komatsuzaki @arankomatsuzaki]

Identifying the Risks of LM Agents with an LM-Emulated Sandbox

Presents a framework that uses a LM to emulate tool execution and enables scalable testing of LM agents against a diverse range of tools and scenarios

proj: https://t.co/6iVW6ONkYH
abs: https://t.co/t7VQVT7VhX

[Sheila McIlraith @SheilaMcIlraith]

This paper was a central contribution of @RToroIcarte 's PhD thesis at U of T, and done in collaboration with Toryn Klassen, @RickValenzano, and supervisor, @SheilaMcIlraith. Early results were first published at ICML18 and AAMAS18. We are proud to have received this recognition.

[Keiran Paster @keirp1]

Meet STEVE-1, an instructable generative model for Minecraft. STEVE-1 follows both text and visual instructions and acts on raw pixel inputs with keyboard and mouse controls. Best of all - it only cost $60 to train!

w/ @Shalev_lif @SirrahChan @jimmybajimmyba @SheilaMcIlraith

[Andrew Wang @andrew_wang10]

Early LLM induced multibillion dollar casualty. What is the value of text-based content, if it can be paraphrased and accessed for free?

https://t.co/YQ5CQr1NNV

[Michael Zhang @michaelrzhang]

Excited to share Boosted Prompt Ensembles! Inspired by boosting algorithms, we propose an algorithm that automatically grows an ensembles of prompts to cover a target problem space.

Led by @silviupitis and with @andrew_wang10 and @jimmybajimmyba

[Hrishi @hrishioa]

What are boosted prompt ensembles, and how can they be used?

New paper released yesterday significantly improves output quality through automating n-shot learning

Paper breakdown with useful takeaways 📃🧵👇

https://t.co/c1igJYqPB4

[Andrew Wang @andrew_wang10]

Generative AI will likely disrupt a number of industries. But as of now, it seems to me the biggest disruption is to existing AI researchers.

[Andrew Wang @andrew_wang10]

Apple launched the app store in 2008. This is the 2023 version.

[Sam Altman @sama]

we are starting our rollout of ChatGPT plugins.

you can install plugins to help with a wide variety of tasks. we are excited to see what developers create!

https://t.co/NQ684Yp2LK