AI Researcher @ Autodesk. Previously Cognitive Science PhD at UC San Diego 2024.
New York
Joined March 2009
- Tweets33
- Following220
- Followers216
- Likes258
Will McCarthy retweeted
When we instruct an agent to design something, its first output may not be precisely what we want. Humans collaborating refine their creations iteratively. Can we instruct an agent to refine its output? Is language the best medium for these instructions? We explore this in mrCAD.
ALT An example from the mrCAD dataset of a designer using drawing and text to iteratively recreate a target design by instructing a maker who manipulates the design. In the first round, the designer only draws an object that resembles the target and the maker creates an approximation of this. In the next round, the designer says "edit the following lines. all circles are the same size", while showing what lines they mean with drawings. After the makes edits the design a bit more, the maker then says that "bottom two circles and exactly opposite each other. all four circles are same size". The maker slightly edits the figure in response, creating something that is close enough to the designer's target.
Will McCarthy retweeted
New #ICCV2025 paper: ✨ Aligning Constraint Generation with Design Intent in Parametric CAD ⚙️
We apply post-training techniques to the task of generating engineering sketch constraints found in parametric CAD, using a constraint solver for verifiable rewards.
Will McCarthy retweeted
Our #UIST2023 Closing keynote will be @StanfordPsych Prof. Judy Fan (@judyefan) who will discuss “Cognitive Tools for Uncovering Useful Abstractions" programs.sigchi.org/uist/202…
Will McCarthy retweeted
@judyefan presenting one of my favorite recent papers looking at how concept libraries inform how we use language #cosmos2023 arxiv.org/abs/2205.05666
Will McCarthy retweeted
Cognitive scientists! You don’t want to miss our #CogSci2023 Workshop: “How does the mind discover useful abstractions?” cogsci-abstractions-workshop… Co-organized w/ the peerless @wkvong + Lio Wong + @marcelomattar!
Will McCarthy retweeted
Job alert!🚨🧠🛠️ We @cogtoolslab @Stanford @StanfordPsych are recruiting a full-time lab manager to join our team Summer/Fall 2023. More information available here: cogtoolslab.github.io/prospe…. Please share widely! 🙏
Will McCarthy retweeted
Job alert!🚨 We @cogtoolslab @UCSD are recruiting a full-stack web applications engineer to build engaging online games that will advance understanding of human cognition and guide development of more human-like AI.
Will McCarthy retweeted
Folks @#CogSci2022, I’ll be giving a talk on work w/ @wang_haoliang @justintheyang @suvir_m @ebiyik_ @DorsaSadigh & @judyefan exploring how people incorporate advice from artificial agents when making physical judgments (paper arxiv.org/abs/2205.11613 repo tinyurl.com/2ca426z6)
When we look at a car, we don’t just see pixels; we see windows, doors, and wheels. In our #CogSci2022 paper, we use the words people use as a window into the ‘library’ of parts they use to represent novel objects like these!
sites.google.com/view/langua…
(1/10)
And it turns out that these “sweet spot” libraries tend to align most strongly (solid line) with people’s descriptions — suggesting people use language that efficiently represents each individual object, AND the set of objects overall. (9/10)
Come see our poster at #CogSci2022, Saturday 1:00-2:40pm, and check out our recorded talk from the @images2symbols workshop on Wednesday!
Arxiv: arxiv.org/abs/2205.05666
Github: github.com/cogtoolslab/lax-c… (10/10)
Will McCarthy retweeted
When people are asked to draw devices, they include more causal parts, more symbols, less structural information, and more spatial distortions if their goal is to explain the device rather than depict it. Research by @hollyahuey et al. at #SPP2022
Will McCarthy retweeted
Day 3: Supercool papers by @hollyahuey & Sebastian Holt investigating how people use graphical representations to communicate about abstract concepts like causality & number. And fascinating study led by @wp_mccarthy exploring links btw perceptual & procedural abstractions.
