Representation Engineering: A Top-Down Approach to AI Transparency
Paper
•
2310.01405
•
Published
•
7
Klee Young PRO
k-young
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Representation Engineering: A Top-Down Approach to AI Transparency
updated
a Space
about 1 month ago
k-young/portraitanimator-pro
published
a Space
about 1 month ago
k-young/portraitanimator-pro
Organizations
upvoted
a
paper
about 1 month ago
updated
a
Space
about 1 month ago
published
a
Space
about 1 month ago
liked
a
Space
about 1 month ago
liked
2
Spaces
about 2 months ago
liked
2
Spaces
2 months ago
liked
2
Spaces
3 months ago
liked
4
Spaces
5 months ago
reacted to
maximuspowers's
post with 🔥
8 months ago
Post
2081
♔ Chess players:
I made an app that encodes chess moves and initiative as musical notes. I'd love to hear ideas from more advanced players about how I could improve this.
My vision for this project was to improve pattern recognition of openings, tactics, and positions through artificial synesthesia.
Please try it out and let me know if you have any ideas for it:
maximuspowers/musical-chess
Thanks😁
I made an app that encodes chess moves and initiative as musical notes. I'd love to hear ideas from more advanced players about how I could improve this.
My vision for this project was to improve pattern recognition of openings, tactics, and positions through artificial synesthesia.
Please try it out and let me know if you have any ideas for it:
maximuspowers/musical-chess
Thanks😁
liked
4
Spaces
9 months ago
reacted to
mikonvergence's
post with 🔥
9 months ago
Post
1703
𝐌𝐄𝐒𝐀 🏔️ 𝐓𝐞𝐱𝐭-𝐛𝐚𝐬𝐞𝐝 𝐭𝐞𝐫𝐫𝐚𝐢𝐧 𝐠𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐦𝐨𝐝𝐞𝐥
MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations (co-registered colour and depth maps) of terrains based on text prompt conditioning.
Work developed by Paul Borne–Pons ( @NewtNewt ) during his joint internship at
Adobe & ESA, and in collaboration with asterisk labs.
🏔️ 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐏𝐚𝐠𝐞 : https://paulbornep.github.io/mesa-terrain/
📝 𝐏𝐫𝐞𝐩𝐫𝐢𝐧𝐭 : https://arxiv.org/abs/2504.07210
🤗 𝐌𝐨𝐝𝐞𝐥 𝐖𝐞𝐢𝐠𝐡𝐭𝐬 : NewtNewt/MESA
💾 𝐃𝐚𝐭𝐚𝐬𝐞𝐭 : Major-TOM/Core-DEM
🧑🏻💻𝐂𝐨𝐝𝐞 : https://github.com/PaulBorneP/MESA
𝐇𝐅 𝐒𝐩𝐚𝐜𝐞: mikonvergence/MESA
MESA is a novel generative model based on latent denoising diffusion capable of generating 2.5D representations (co-registered colour and depth maps) of terrains based on text prompt conditioning.
Work developed by Paul Borne–Pons ( @NewtNewt ) during his joint internship at
Adobe & ESA, and in collaboration with asterisk labs.
🏔️ 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐏𝐚𝐠𝐞 : https://paulbornep.github.io/mesa-terrain/
📝 𝐏𝐫𝐞𝐩𝐫𝐢𝐧𝐭 : https://arxiv.org/abs/2504.07210
🤗 𝐌𝐨𝐝𝐞𝐥 𝐖𝐞𝐢𝐠𝐡𝐭𝐬 : NewtNewt/MESA
💾 𝐃𝐚𝐭𝐚𝐬𝐞𝐭 : Major-TOM/Core-DEM
🧑🏻💻𝐂𝐨𝐝𝐞 : https://github.com/PaulBorneP/MESA
𝐇𝐅 𝐒𝐩𝐚𝐜𝐞: mikonvergence/MESA
- 2 replies