🎉Excited to share that our paper "𝐇𝐮𝐦𝐚𝐧-𝐀𝐥𝐢𝐠𝐧𝐞𝐝 𝐈𝐦𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥𝐬 𝐈𝐦𝐩𝐫𝐨𝐯𝐞 𝐕𝐢𝐬𝐮𝐚𝐥 𝐃𝐞𝐜𝐨𝐝𝐢𝐧𝐠 𝐟𝐫𝐨𝐦 𝐭𝐡𝐞 𝐁𝐫𝐚𝐢𝐧" has been accepted to #ICML2025! 🔗 Preprint Link: arxiv.org/abs/2502.03081 Huge thanks to my co-authors!

I’m attending #NeurIPS in Vancouver from Tuesday to Sunday. I’ll be presenting our paper “Amplified Early Stopping Bias: Overestimated Performance with Deep Learning” in the Scientific Methods for Understanding Deep Learning Workshop. Let’s meet especially if you are interested in Neuroscience!