Kirill Bykov
@kirillbykov.bsky.social
📤 346
📥 198
📝 10
PhD student in Interpretable ML @UMI_Lab_AI, @bifoldberlin, @TUBerlin
pinned post!
Personal news: I have defended my PhD thesis “Explaining Representations in Deep Neural Networks” at
@tuberlin.bsky.social
with summa cum laude (with distinction). From August, I’ll start a Postdoc at
@tumunich.bsky.social
in
@eml-munich.bsky.social
, focusing on Mechanistic Interpretability ✨
5 months ago
1
10
0
San Diego 🇺🇸 or Mexico City 🇲🇽 for
#NeurIPS2025
? We got you covered either way 😎 On Dec 3rd: 🇲🇽
@dilya.bsky.social
present our work on the fragility of Mech Interp in Mexico 🇺🇸
@lkopf.bsky.social
present our work on polysemanticity in San Diego I am not there this year, so I‘ll be cheering from afar!
27 days ago
0
6
1
reposted by
Kirill Bykov
Dilyara Bareeva
about 1 month ago
✈️🇲🇽 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! 🚨
1
9
4
reposted by
Kirill Bykov
Laura Kopf
28 days ago
I’m at
#NeurIPS
in San Diego this week! Come see our poster on feature interpretability. Find
@eberleoliver.bsky.social
and me at: 🪧Poster Session 1 @ Exhibit Hall C,D,E #1015 Wed 3 Dec, 11 am - 2 pm 🪧Poster @ Mech Interp Workshop Upper Level Room 30A-E Sun 7 Dec, 8 am - 5 pm
1
11
3
reposted by
Kirill Bykov
Explainable AI Berlin
about 1 month ago
Manipulating Feature Visualizations with Gradient Slingshots
@dilya.bsky.social
Marina MC Höhne, Alexander Warnecke
@lpirch.bsky.social
Klaus-Robert Müller
@rieck.mlsec.org
@slapuschkin.bsky.social
@kirillbykov.bsky.social
👇
1
4
3
reposted by
Kirill Bykov
Explainable AI Berlin
about 1 month ago
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
@lkopf.bsky.social
@nfel.bsky.social
@kirillbykov.bsky.social
@philinelb.bsky.social
Anna Hedström, Marina Höhne
@eberleoliver.bsky.social
👇
1
5
2
reposted by
Kirill Bykov
Laura Kopf
3 months ago
Happy to share that our PRISM paper has been accepted at
#NeurIPS2025
🎉 In this work, we introduce a multi-concept feature description framework that can identify and score polysemantic features. 📄 Paper:
arxiv.org/abs/2506.15538
#NeurIPS
#MechInterp
#XAI
loading . . .
1
30
7
reposted by
Kirill Bykov
Philine Lou Bommer
5 months ago
🚨New paper 🚨 We are happy to announce that our paper “Deep Learning meets Teleconnections: Improving S2S Predictions for European Winter Weather” has been published at Machine Learning: Earth
@ioppublishing.bsky.social
📄
iopscience.iop.org/article/10.1...
💻
github.com/philine-bomm...
loading . . .
Radware Bot Manager Captcha
To ensure we keep this website safe, please can you confirm you are a human by ticking the box below.
https://iopscience.iop.org/article/10.1088/3049-4753/ade9c2
1
4
2
Personal news: I have defended my PhD thesis “Explaining Representations in Deep Neural Networks” at
@tuberlin.bsky.social
with summa cum laude (with distinction). From August, I’ll start a Postdoc at
@tumunich.bsky.social
in
@eml-munich.bsky.social
, focusing on Mechanistic Interpretability ✨
5 months ago
1
10
0
Check out our new work! Proud to share what we’ve been up to 👉
add a skeleton here at some point
6 months ago
0
3
0
reposted by
Kirill Bykov
Laura Kopf
about 1 year ago
I’ll be presenting our work at
@neuripsconf.bsky.social
in Vancouver! 🎉 Join me this Thursday, December 12th, in East Exhibit Hall A-C, Poster #3107, from 11 a.m. PST to 2 p.m. PST. I'll be discussing our paper “CoSy: Evaluating Textual Explanations of Neurons.”
1
10
1
I am not attending
#NeurIPS2024
, but I encourage everyone interested in
#XAI
and
#MechInterp
to check out our paper on evaluating textual descriptions of neurons! Join
@lkopf.bsky.social
, Anna Hedström, and Marina Marie-Claire Höhne on Thu 09.12, 1 p.m. to 4 p.m. CST at East Exhibit Hall A-C #3107!
about 1 year ago
1
12
0
reposted by
Kirill Bykov
naia
about 1 year ago
i exclusively consent to my tweets being used for training neural networks. if you are not a neural network, stop reading this immediately
17
310
45
reposted by
Kirill Bykov
Oliver Eberle
about 1 year ago
add a skeleton here at some point
17
25
5
you reached the end!!
feeds!
log in