EPISODE · Apr 14, 2025 · 17 MIN
Steering CLIP's vision transformer with sparse autoencoders
from Arxiv Papers · host Igor Melnyk
This study explores sparse autoencoders in vision models, revealing unique processing patterns and enhancing steerability, leading to improved performance in vision disentanglement tasks and defense strategies. https://arxiv.org/abs//2504.08729 YouTube: https://www.youtube.com/@ArxivPapers TikTok: https://www.tiktok.com/@arxiv_papers Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016 Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
Embed this episode
Ready to play
Steering CLIP's vision transformer with sparse autoencoders
No transcript for this episode yet
Similar Episodes
No similar episodes found.