Kirill Bykov
@kirillbykov.bsky.social
PhD student in Interpretable ML @UMI_Lab_AI, @bifoldberlin, @TUBerlin
Pinned
Kirill Bykov
@kirillbykov.bsky.social
· Jul 24
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 ✨
From August, I’ll start a Postdoc at @tumunich.bsky.social in @eml-munich.bsky.social, focusing on Mechanistic Interpretability ✨
Reposted by Kirill Bykov
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
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
September 19, 2025 at 12:02 PM
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
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
Reposted by Kirill Bykov
🚨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...
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...
Radware Bot Manager Captcha
To ensure we keep this website safe, please can you confirm you are a human by ticking the box below.
iopscience.iop.org
August 5, 2025 at 7:19 AM
🚨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...
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...
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 ✨
From August, I’ll start a Postdoc at @tumunich.bsky.social in @eml-munich.bsky.social, focusing on Mechanistic Interpretability ✨
July 24, 2025 at 8:38 AM
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 ✨
From August, I’ll start a Postdoc at @tumunich.bsky.social in @eml-munich.bsky.social, focusing on Mechanistic Interpretability ✨
Check out our new work! Proud to share what we’ve been up to 👉
🔍 When do neurons encode multiple concepts?
We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity.
📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
arxiv.org/abs/2506.15538
🧵 (1/7)
We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity.
📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
arxiv.org/abs/2506.15538
🧵 (1/7)
June 19, 2025 at 3:20 PM
Check out our new work! Proud to share what we’ve been up to 👉
Reposted by Kirill Bykov
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.”
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.”
December 11, 2024 at 6:43 AM
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.”
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.”
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!
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!
December 9, 2024 at 3:26 PM
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!
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!
Reposted by Kirill Bykov
i exclusively consent to my tweets being used for training neural networks. if you are not a neural network, stop reading this immediately
November 28, 2024 at 2:59 AM
i exclusively consent to my tweets being used for training neural networks. if you are not a neural network, stop reading this immediately
Reposted by Kirill Bykov
