Lamberto Ballan
lambertoballan.bsky.social
Researcher in Computer Vision, Machine Learning and Embodied AI / Associate Prof of CS @UniPadova since 2017 / @ellis.eu member Previously: EU MSCA Fellow 2014-17 @Stanford and @UniFirenze 📍Padova, Italy 🔗 http://vimp.math.unipd.it/
👤 Joined on 20 November 2024
576
Followers
176
Following
19
Total Posts
📜 Kullanıcı Geçmişi
- 20 Kas 2024, 15:04
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@lambertoballan.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
New papers on recurrent transformers: arxiv.org/pdf/2606.21562 (ours): train full Tr, distill -> rec Tr arxiv.org/pdf/2608.02870 train full and rec jointly, min. coherence arxiv.org/pdf/2606.06479 train rec Tr with predictive obj. arxiv.org/pdf/2608.08888 train full Tr, add rec latents, multi-pass
Show Post
Your camera leaves fingerprints on every photo. Vision encoders learned to read them. Read about the bad and the good sides of it. "Invisible Shortcuts: Why Vision Encoders Know Your Camera" has been accepted at ECCV 2026. Paper: arxiv.org/pdf/2608.05424 @eccv.bsky.social #ECCV2026
Show Post
Our #ECCV2026 Whareformer paper tackles long-term object tracking in Egocentric videos 🎓https://arxiv.org/abs/2607.08537 see Dima's thread below 🔽 joint work w Jacob Chalk, @saptarshisinha.bsky.social @dimadamen.bsky.social from Bristol & @skamalas.bsky.social from @naverlabseurope.bsky.social
Show Post
What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility Filippo Ziliotto, Luciano Serafini, @lambertoballan.bsky.social, Tommaso Campari tl;dr: early layers->3D-aware scene representation; late layers->co-visibility; VGGT+MoE head arxiv.org/abs/2607.09503
Show Post
Inspired by @jbhuang0604.bsky.social's Awesome-Tips webpage and his encouragement, I put together a webpage collecting #KostasThoughts posts from over the years. Hope you find them useful! #KostasThoughts: csprofkgd.github.io/kostas-thoug...
Show Post