Karl D.D. Willis
@KarlDD
Followers
420
Following
79
Media
42
Statuses
110
Senior Research Manager, Autodesk AI Lab
Joined May 2009
At #ICML this week @SamXu03799145 will present our latest work that generates solid CAD models in a controllable manner. Check out the tweet below for details!.
In our latest #ICML2023 paper "Hierarchical Neural Coding for Controllable CAD Model Generation" we learn the design intent from different CAD hierarchies in a self-supervised manner, and demonstrate its application on multiple tasks e.g. autocomplete.
1
1
23
The ICML Poster session is Thu 27 Jul 2023 at 10:30 a.m. HST — noon HST:
0
0
1
RT @Design_for_AM: Latest interview in the CDFAM speaker series with @KarlDD on his AI research at Autodesk. Karl w….
linkedin.com
Latest interview in the CDFAM speaker series with Karl D.D. Willis on his AI research at Autodesk. https://lnkd.in/grBZKVPP Karl will be speaking more about his work at the Autodesk Research AI Lab...
0
1
0
Interested in an internship at Autodesk Research? We have three ML roles for Summer 2023 in SF and Toronto. Data Acquisition and ML Research. Large Language Models. Machine Learning Research.
0
8
37
If you are attending SIGGRAPH Asia check out our talk during the “Computer-Aided Design” session: Wed Dec 7, 17:00-18:30 KST. I'll be there and happy to meet with anyone!
0
0
3
For a nice overview of our work, check out this article from MIT:
1
0
2
Using this reduced search space we can efficiently discover feasible assembly plans. To evaluate our approach we take it to another level by testing on a dataset of 10,000+ assemblies and show state-of-the-art results.
1
0
5
We generate assembly plans by disassembling CAD assemblies part-by-part. The key idea is to use a contact-rich simulation with a discrete number of approximate force directions to pull parts away from the main assembly.
1
0
5
Our latest collaboration with @MIT_CSAIL and @TAMU led by @YunshengTian will be presented at SIGGRAPH Asia today! . We want to make it easier to assemble objects AND to disassemble them for end-of-life recycling and part reuse.
Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly.abs: .project page:
1
11
75
If you are at #NeurIPS2022 this week, check out some of the work the Autodesk AI Lab team has been doing on robustness, evaluating graph generative models, and communicating natural programs!.
Autodesk Research AI Lab has 3 papers accepted at #NeurIPS2022! .✅ MaskTune: Mitigating Spurious Correlations. ✅ Evaluating Graph Generative Models. ✅ Communicating Natural Programs to Humans & Machines
0
1
9
RT @ADSKResearch: AI-powered design tools are essential to Autodesk’s future offerings, and the work being published by the AI Lab at top-t….
0
2
0
RT @evanthebouncy: want to get into program synthesis but don't know how to started? I wrote a minimalist intro to modern program synthesis….
evanthebouncy.github.io
a bare minimum introduction to modern program synthesis
0
17
0
Large language model failure mode of the month: Mode collapse to all emoji output all the time. Not helpful 🤷♂️😫🤬 @evanthebouncy.
0
0
4
Collage is a whole lot of fun! Chatting to @_joelsimon and @ev_ancasey was even more so. Super cool/smart team making progress on the grand challenge of how we interact with AI to create.
We’re hard at work on a new way to make generative art, and are excited to share our first prototype!. Create any scene you can imagine with a simple collage and a prompt. Try it out!
1
0
5
📢 We are hiring in the Autodesk AI Lab. Doubling down on what @adam_gaier said, for all those folks that are mission driven to create tools for designing better buildings, cars, devices etc and want to use AI/ML to make it happen.
Come work with me at Autodesk! . i'll pick you up at the intersection of AI and design. apply here ⬇️.
0
3
5
Fun collaboration between the Autodesk AI Lab and @jiajunwu_cs lab at Stanford! Learning to assemble (and also disassemble) is both technically challenging and impactful for manufacturing efficiency and ensuring products don't have a negative impact at end-of-life.
🧠 AI for Visual LEGO Manual to a Machine-Executable Plan 🧠. 👉 The authors present a novel learning-based framework, the Manual-to-Executable-Plan Network (MEPNet), which reconstructs the assembly steps from a sequence of manual images. 🧵👇
0
2
8
For folks who are still at #ICML2022 I'll be giving a talk today at the Workshop on Machine Learning for Computational Design. Exciting line up!.
mlcompdesign.github.io
ICML 2022 Workshop
0
1
6
13/ Finally a huge thank you to my co-authors @SamXu03799145 @YasutakaFuruka1 and my Autodesk colleagues @pradeeppyro @jglambourne @chinyich.
0
0
2