ExplainableML's profile picture. Institute for Explainable Machine Learning @HelmholtzMunich and Interpretable and Reliable Machine Learning group @TU_Muenchen

Explainable Machine Learning

@ExplainableML

Institute for Explainable Machine Learning @HelmholtzMunich and Interpretable and Reliable Machine Learning group @TU_Muenchen

Explainable Machine Learning 님이 재게시함

2 papers accepted at NeurIPS 2025 🎉 🔹 Manipulating Feature Visualizations with Gradient Slingshots 🔹 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

kirill_bykov's tweet image. 2 papers accepted at NeurIPS 2025 🎉 

🔹 Manipulating Feature Visualizations with Gradient Slingshots
🔹 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

Explainable Machine Learning 님이 재게시함

Reward hacking is challenging when fine-tuning few-step Diffusion models. Direct fine-tuning on rewards can create artifacts that game metrics while degrading visual quality. We propose Noise Hypernetworks as a theoretically grounded solution, inspired by test-time optimization.


Explainable Machine Learning 님이 재게시함

💫 After four PhD years on all things multimodal, pre- and post-training, I’m super excited for a new research chapter @GoogleDeepMind 🇨🇭! Biggest thanks to @zeynepakata and @OriolVinyalsML for all the guidance, support, and incredibly eventful and defining research years ♥️!

confusezius's tweet image. 💫 After four PhD years on all things multimodal, pre- and post-training, I’m super excited for a new research chapter @GoogleDeepMind 🇨🇭!

Biggest thanks to @zeynepakata and @OriolVinyalsML for all the guidance, support, and incredibly eventful and defining research years ♥️!
confusezius's tweet image. 💫 After four PhD years on all things multimodal, pre- and post-training, I’m super excited for a new research chapter @GoogleDeepMind 🇨🇭!

Biggest thanks to @zeynepakata and @OriolVinyalsML for all the guidance, support, and incredibly eventful and defining research years ♥️!
confusezius's tweet image. 💫 After four PhD years on all things multimodal, pre- and post-training, I’m super excited for a new research chapter @GoogleDeepMind 🇨🇭!

Biggest thanks to @zeynepakata and @OriolVinyalsML for all the guidance, support, and incredibly eventful and defining research years ♥️!

Loading...

Something went wrong.


Something went wrong.