Longer than a tweet, looser than a paper.
A walkthrough of ExPLoRe, our ECCV 2026 paper on per-patch loss weighting for masked image modeling. It covers the idea, the main ablations, and the parts I'm still unsure about.
15 min read
Five and a half years of an ML PhD, six lessons that aren't in any of the papers. The kind of things I keep telling friends still in the program.
10 min read
The long version of my background, from Greece to a PhD in Tennessee, with a few detours in between.
8 min readA walkthrough of ExPLoRe, our ECCV 2026 paper on per-patch loss weighting for masked image modeling. It covers the idea, the main ablations, and the parts I'm still unsure about.
Five and a half years of an ML PhD, six lessons that aren't in any of the papers. The kind of things I keep telling friends still in the program.
The long version of my background, from Greece to a PhD in Tennessee, with a few detours in between.
A fresh site, a fond farewell to the old one, and a small tease of what's coming next.
New posts are brewing. Check back soon.
Stay in the loop. Posts, papers, projects, and site updates.
