Yubin Xie @yubinx.bsky.social · 23/12/2025Happy holidays. Our ICLR 2026 workshop, I Can’t Believe It’s Not Better, is now open for submissions. If you’ve been thinking about where LLMs still fall short, details are on the website. 100
Yubin Xie @yubinx.bsky.social · 15/12/2025Glad to share that our I Can’t Believe It’s Not Better workshop has been accepted at ICLR 2026. This year we focus on creating space to examine where large language models still fall short and why negative results and careful analysis matter. Call for papers coming soon.shorturl.atICLR Workshop 2026Current LLMs still fall short in surprising ways. Let’s face those gaps, learn from failures, and move the field forward together! 011
Yubin Xie @yubinx.bsky.social · 22/01/2025Hey everyone! I’m co-organizing the “I Can’t Believe It’s Not Better” #ICLR2025 @iclr-conf.bsky.social workshop, and we’re still accepting submissions on negative results in real life #DeepLearning application. Time is flying—Feb 3, 2025 is almost here! Get the details at shorturl.at/OpQns.shorturl.atICLR Workshop 2025 - Call for PapersWe invite researchers and industry professionals to submit their papers on negative results, failed experiments, and unexpected challenges encountered in applying deep learning to real-world problems ... 001
Reposted by Yubin XieI Can’t Believe It’s Not Better Initiative @icbinb.bsky.social · 10/01/2025Please spread the word! Our “I Can’t Believe It’s Not Better” #ICLR2025 workshop @iclr-conf.bsky.social is now accepting submissions on unexpected results in applied #DeepLearning. Share your tough lessons and unexpected outcomes by Feb 3, 2025. More info: shorturl.at/tD1jushorturl.atICLR Workshop 2025 - Call for PapersWe invite researchers and industry professionals to submit their papers on negative results, failed experiments, and unexpected challenges encountered in applying deep learning to real-world problems ... 033
Yubin Xie @yubinx.bsky.social · 18/12/2024Biology is spatial —and so shall a foundation model be.🌍I’m excited to share OCTO-VirtualCell, our latest model and the Celleporter platform @Noetik —work I’m deeply proud of and believe is transformative for spatial biology. report: noetik.ai/octo-vc demo: celleporter.noetik.ainoetik.aiOCTO-vcCelleporter is a simulator of spatial biology that predicts gene expression patterns for virtual cells embedded in patient tissue samples. 231
Yubin Xie @yubinx.bsky.social · 17/12/2024The call for papers is out for our “I Can’t Believe It’s Not Better” #ICLR2025 workshop @iclr-conf.bsky.social . Don’t miss this chance to highlight challenges in applying deep learning & foundation models in real life. 062
