Feyza Yavuz
@fyavuz1.bsky.social
PhD Student @naverlabseurope.bsky.social & INRIA Thoth Team MSc ODTU CEng.
Attending #ECCV2026? Want to know why your favorite vision models learn to encode camera acquisition and processing traces? Come meet our team! 👇 @eccv.bsky.social
Looking for a research scientist role in a beautiful and mountainous landscape? The visual representation learning team @naverlabseurope.bsky.social is hiring!
Our #ECCV2026 IDeaL paper tackles Data-Free Multi-Teacher Distillation 🎓 arxiv.org/abs/2608.24759 see Bülent's thread below 🔽 joint work w @fyavuz1.bsky.social @mbsariyildiz.bsky.social at @naverlabseurope.bsky.social
Mert Bulent Sariyildiz@mbsariyildiz.bsky.social · 2mo ago🧐 Can you distill knowledge from 4 vision teachers into one student using ZERO real images? 🥳 Turns out: YES, and surprisingly well. 📣 Our ECCV 2026 paper "IDeaL" closes most of the gap with real-image distillation, using optimized structured noise.
🧐 Can you distill knowledge from 4 vision teachers into one student using ZERO real images? 🥳 Turns out: YES, and surprisingly well. 📣 Our ECCV 2026 paper "IDeaL" closes most of the gap with real-image distillation, using optimized structured noise.
Excited to share our work, IDeaL! Big thanks to @mbsariyildiz.bsky.social and @dlarlus.bsky.social for the guidance and support from day one. At ECCV? We're in Poster Session 2, Thu Sep 10. Come say hi! Paper: arxiv.org/abs/2608.24759 Project page: blisgard.github.io/ideal_project/
Mert Bulent Sariyildiz@mbsariyildiz.bsky.social · 2mo ago🧐 Can you distill knowledge from 4 vision teachers into one student using ZERO real images? 🥳 Turns out: YES, and surprisingly well. 📣 Our ECCV 2026 paper "IDeaL" closes most of the gap with real-image distillation, using optimized structured noise.