Dilyara Bareeva (@dilya.bsky.social)

Dilyara Bareeva

@dilya.bsky.social

PhD Candidate in Interpretability @FraunhoferHHI | 📍Berlin, Germany dilyabareeva.github.io

799 followers 503 following5 posts

@dilya.bsky.social

29 Nov 2025

✈️🇲🇽 Next Wednesday (Dec 3), 1–4 p.m. CST, I’ll be presenting Manipulating Feature Visualizations with Gradient Slingshots at NeurIPS 2025 in Mexico City! Feature Visualization has long been a staple interpretability tool. Our work shows it’s far from reliable! 🚨

Huge thanks to my fantastic co-authors Marina MC Höhne, Alexander Warnecke, @lpirch.bsky.social, Klaus-Robert Müller, @rieck.mlsec.org, @slapuschkin.bsky.social, @kirillbykov.bsky.social, and to the UMI Lab, @aifraunhoferhhi.bsky.social, @xai-berlin.bsky.social and @bifold.berlin for the support!

Dilyara Bareeva

@dilya.bsky.social

29 Nov 2025

Paper: openreview.net/forum?id=Tgc... Code: github.com/dilyabareeva...

openreview.netManipulating Feature Visualizations with Gradient SlingshotsFeature Visualization (FV) is a widely used technique for interpreting concepts learned by Deep Neural Networks (DNNs), which synthesizes input patterns that maximally activate a given feature....

Our lightweight adversarial fine-tuning attack lets you bend a feature to visualize any arbitrary concept. Off-manifold, we impose a hyperbolic activation landscape with its optimum at the target, while preserving on-distribution activations through a weighted two-term loss. 🕵️‍♀️

Dilyara Bareeva

@dilya.bsky.social

13 Dec 2024

Sadly, I wasn’t able to make it to NeurIPS this year. For anyone attending, check out our quanda poster at the ATTRIB workshop tomorrow (Saturday) from 3 to 4:30 pm, presented by Galip Ümit Yolcu and Anna Hedström! GitHub: github.com/dilyabareeva... Paper: arxiv.org/abs/2410.07158

github.comGitHub - dilyabareeva/quanda: A toolkit for quantitative evaluation of data attribution methods.A toolkit for quantitative evaluation of data attribution methods. - dilyabareeva/quanda

You are up to date.