The gap was never fully closed between thought and expression, between intent and execution.
And the tool I really wanted still did not exist.
(5/5)
English
Chin-Yi Cheng
64 posts
Chin-Yi Cheng
@chinyich
co-founder and ceo at illoca | ai for aec | ex-google deepmind | ex-autodesk ai lab
Katılım Eylül 2016
305 Takip Edilen437 Takipçiler
If a tool really matched the way architects think, there would be no reason to keep leaving it just to design freely.
Looking back, I think that tension stayed with me for so long because it pointed to something deeper than software adoption or personal preference. (4/5)
English
I’ve been reflecting on my past work lately.
What stands out to me is not how much has changed, but how often the same question keeps coming back.
(1/5)
English
Chin-Yi Cheng retweetledi
Over the past year, I've been compiling some "alchemist's notes" on deep learning. Right now it covers basic optimization, architectures, and generative models.
Focus is on learnability -- each page has nice graphics and an end-to-end implementation.
notes.kvfrans.com
English
Here is the JD:
👉 cyclic-crater-fdb.notion.site/Software-Engin…
Know someone amazing who might be interested? Feel free to tag or share—thank you!
(3/3)
English
If you're excited by:
- Crafting interactive user experiences
- Shaping early engineering culture
- Working closely with a small, fast-moving team
- Building solutions that impact billions of people
We'd love to talk!
(2/3)
English
We're hiring a Software Engineer to join our team! 🚀
We're building a new product at the intersection of design and AI, and we're looking for someone who loves creating innovative experiences that solve complex, real-world challenges.
(1/3)
English
Chin-Yi Cheng retweetledi
🚀 Excited to unveil our latest work: WaLa! A simple yet powerful approach. We're also open-sourcing billion-parameter models trained on 10M 3D shapes across various conditioning modalities! Can't wait to see what the community creates! 🌟
🔗 arxiv.org/pdf/2411.08017
#AI #MachineLearning #OpenSource #3DGeneration
English
Chin-Yi Cheng retweetledi
*Shortcut models* are a plug-and-play replacement for diffusion models that can generate in a single step (or more). This speeds up inference by up to 128x.
Shortcut models are trained end-to-end, and do not require a separate distillation phase or learning schedules.
English
Chin-Yi Cheng retweetledi
Aloha! Our #ICML workshop on #AI & #HCI is happening this Saturday in room 311. Check out our workshop page at sites.google.com/view/aihci/sch… for a detailed schedule! We have a fantastic lineup of speakers and 50+ in-person poster presentations.
Bryan Wang@bryanhaoenwang
Excited to share that we are organizing the AI & HCI workshop at #ICML2023 in Hawaii! We have now started to accept paper submissions with 2-8 pages on topics at the intersection of #AI and #HCI. Submission deadline: May 4th, 2023. Website: sites.google.com/view/aihci
English
I might start to use Bard after each whiteboarding session and after cooking🍜
English
Is there a high-level yet precise way for designers to control generative models? Can we generate layouts by simply sketching several guidelines?
Please check our paper at ICML--PLay: Parametrically Conditioned Layout Generation using Latent Diffusion.
arxiv.org/abs/2301.11529
GIF
English
Chin-Yi Cheng retweetledi
Excited to share that we are organizing the AI & HCI workshop at #ICML2023 in Hawaii! We have now started to accept paper submissions with 2-8 pages on topics at the intersection of #AI and #HCI. Submission deadline: May 4th, 2023.
Website: sites.google.com/view/aihci
Yang Li@yangli169
This is happening! Our workshop on AI & HCI is accepted by ICML 2023, Honolulu, Hawaii. icml.cc/Conferences/20… We have assembled a great collection of speakers across ML and HCI. More details and CFP will follow.
English
Thanks to everyone who expressed interest. We'll try our best to select potential candidates and contact them for the next steps.
English
Our team has an opening for the Google 2023 Student Researcher Program!
If you're interested in research topics including (but not limited to) AI x Design, multimodal, and generative models, please feel free to dm me.
English
Chin-Yi Cheng retweetledi
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.
AK@_akhaliq
Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly abs: arxiv.org/abs/2211.03977 project page: assembly.csail.mit.edu
English
Chin-Yi Cheng retweetledi
Powderworld is a lightweight simulation environment for understanding AI generalization, supporting:
- modular & emergent ruleset
- expressive RL task space
- 10k timesteps/sec via GPU
Paper: arxiv.org/abs/2211.13051
Blog + Online Demo: kvfrans.com/static/powder/
English