Nicky Kriplani
I am a second-year PhD student at Cornell Tech. Before that, I studied computer science at the NYU Tandon School of Engineering, and I was a Software Engineer at Atlassian, where I worked on automating the release process for Jira Align.
My research interests are broadly in computer vision and the messy aspects of real-world ML such as fairness, privacy, and abuse.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Department of Computer Science
Ph.D. StudentAug 2025 - present -
B.S. in Computer ScienceAug 2021 - May 2024
Experience
-
Software EngineerJuly 2024 - Aug 2025
News
Selected Publications (view all )
When Are Concepts Erased From Diffusion Models?
Kevin Lu, Nicky Kriplani, Rohit Gandikota, Minh Pham, David Bau, Chinmay Hegde, Niv Cohen
NeurIPS 2025 (Poster)
This work analyzes the mechanisms of existing concept erasure methods using a suite of probing methods to assess how much knowledge is remaining in the model. Overall, we find that many of the tested methods simply steer outputs away from the underlying knowledge as opposed to actually removing it.
When Are Concepts Erased From Diffusion Models?
Kevin Lu, Nicky Kriplani, Rohit Gandikota, Minh Pham, David Bau, Chinmay Hegde, Niv Cohen
NeurIPS 2025 (Poster)
This work analyzes the mechanisms of existing concept erasure methods using a suite of probing methods to assess how much knowledge is remaining in the model. Overall, we find that many of the tested methods simply steer outputs away from the underlying knowledge as opposed to actually removing it.
SolidMark: Evaluating Image Memorization in Generative Models
Nicky Kriplani, Minh Pham, Gowthami Somepalli, Chinmay Hegde, Niv Cohen
arXiv preprint arXiv:2503.00592
This paper introduces SolidMark, a new evaluation method that provides per-image memorization scores to better detect when diffusion models have memorized specific training images. We use SolidMark to re-evaluate existing memorization mitigation techniques and demonstrate its ability to assess pixel-level memorization in generative models.
SolidMark: Evaluating Image Memorization in Generative Models
Nicky Kriplani, Minh Pham, Gowthami Somepalli, Chinmay Hegde, Niv Cohen
arXiv preprint arXiv:2503.00592
This paper introduces SolidMark, a new evaluation method that provides per-image memorization scores to better detect when diffusion models have memorized specific training images. We use SolidMark to re-evaluate existing memorization mitigation techniques and demonstrate its ability to assess pixel-level memorization in generative models.