CS PhD Candidate at Cornell Tech | Previously a Software Engineer at Atlassian | https://nitter.gq/t.co/NTpmNu24kM
Joined May 2024
- Tweets11
- Following42
- Followers16
- Likes10
Nicky Kriplani retweeted
Where on the floorplan was this photo taken? 📍
Excited to share SceneAligner, accepted to #NeurIPS2026!
We tackle this by reconstructing the scene in 3D and aligning it to the floorplan. Joint work with @ruojin8 @ElorHadar [1/8]
How well do 3D foundation models reconstruct architecture from around the world? 🌍
Our #NeurIPS2026 paper introduces ArchWorld, a geographically diverse 3D scene benchmark, and ArchAttend, an inference-time intervention that improves regional disparities.
🧵
Applied to Depth Anything 3, ArchAttend
1) cuts median normalized Chamfer Distance by 13.9%
2) shrinks the regional gap by 38.2%
3) shrinks the architecture-type gap by 33.5%
Joint work with @YiwenZhangYZ, @ang3linawang, and @ElorHadar at Cornell Tech.
Paper: arxiv.org/abs/2610.22514
Project Page: arch-world.github.io
Code: github.com/Cornell-VAILab/Ar…
Data: huggingface.co/datasets/Arch…
Nicky Kriplani retweeted
We tested several unlearning methods and found none of them really erase knowledge from the model - they simply hide it! 🧐
What does this mean? We must tread carefully with unlearning research within diffusion models🚨
Here is what we learned 🧵👇(led by @kevinlu4588)
ALT Title slide reading "When Are Concepts Erased From Diffusion Models?"
Excited to share our paper “When Are Concepts Erased from Diffusion Models?” at @NeurIPSConf!
We introduce two conceptual models for erasure mechanisms in diffusion models, and a suite of probes to recover supposedly forgotten concepts.
Project website: unerasing.baulab.info/
Nicky Kriplani retweeted
Excited to share our paper “When Are Concepts Erased from Diffusion Models?” at @NeurIPSConf!
We introduce two conceptual models for erasure mechanisms in diffusion models, and a suite of probes to recover supposedly forgotten concepts.
Project website: unerasing.baulab.info/