
Explainable Machine Learning
@ExplainableML
Institute for Explainable Machine Learning @HelmholtzMunich and Interpretable and Reliable Machine Learning group @TU_Muenchen
قد يعجبك
2 papers accepted at NeurIPS 2025 🎉 🔹 Manipulating Feature Visualizations with Gradient Slingshots 🔹 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

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.
💫 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 ♥️!



United States الاتجاهات
- 1. Ohtani 218K posts
- 2. Dodgers 263K posts
- 3. World Series 61.9K posts
- 4. Carson Beck 16.6K posts
- 5. Emiru 7,714 posts
- 6. Miami 101K posts
- 7. Louisville 28.4K posts
- 8. Nebraska 17.8K posts
- 9. Brewers 56.7K posts
- 10. Babe Ruth 3,502 posts
- 11. NOCHE IS BACK 29.4K posts
- 12. NLCS 62.5K posts
- 13. Massie 31.1K posts
- 14. #HeartofTaehyung 23K posts
- 15. #BostonBlue 7,860 posts
- 16. George Santos 85.4K posts
- 17. Rhule 4,688 posts
- 18. 3 HRs 10.1K posts
- 19. Sam Harris 1,048 posts
- 20. #SmackDown 59K posts
قد يعجبك
-
Zeynep Akata
@zeynepakata -
ELLIS
@ELLISforEurope -
AI Conference DL Countdown
@DlCountdown -
Mihaela van der Schaar
@MihaelaVDS -
Michael Black
@Michael_J_Black -
Been Kim
@_beenkim -
Cambridge MLG
@CambridgeMLG -
Yarin
@yaringal -
UvA AMLab
@AmlabUva -
Oana-Maria Camburu
@oanacamb -
Accepted papers at TMLR
@TmlrPub -
Georgios Pavlakos
@geopavlakos -
Federico Tombari
@fedassa -
Christoph Molnar 🦋 christophmolnar.bsky.social
@ChristophMolnar -
Kate Saenko
@kate_saenko_
Something went wrong.
Something went wrong.