Inlay

Postdoc @hertie-ai.bsky.social | PhD @maxplanckcampus.bsky.social & unituebingen.bsky.social | Interested in Computational Neuroscience, Data Science & AI 🧠🤖 | Science Podcast https://linktr.ee/i_am_scientist 🎙️🧬

Yongrong Qiu, Na Zhou, Mels Akhmetali,@dgonschorek.bsky.social @neuro-cam.bsky.social Anton Sumser,Marie Vallens, Cathryn Cadwell,Fabrizio Gabbiani,Maximilian Jösch @andreastolias.bsky.social @philipp.hertie.ai @teuler.bsky.social @sinzlab.bsky.social @viajake.bsky.social @katrinfranke.bsky.social

𝗨𝘀𝗲 𝗼𝘂𝗿 𝗺𝗼𝗱𝗲𝗹 𝗮𝘀 𝗮 𝘃𝗶𝗿𝘁𝘂𝗮𝗹 𝗹𝗮𝗯 𝗯𝗲𝗻𝗰𝗵: The trained digital twin model lets you feed in any stimulus you're curious about and generate your own neural responses. Feed in your own stimulus and see what the model predicts 👇 💻 Colab notebook: colab.research.google.com/drive/1k9411... (4/🧵)

Huge thanks to an incredible cross-institutional team spanning Stanford, University of Tübingen, University of Göttingen, Baylor College of Medicine, LMU Munich, UCSF, ISTA Austria, and Universitätsklinikum Tübingen. (5/🧵)

𝘞𝘩𝘢𝘵 𝘪𝘧 𝘺𝘰𝘶 𝘤𝘰𝘶𝘭𝘥 𝘵𝘦𝘴𝘵 𝘺𝘰𝘶𝘳 𝘩𝘺𝘱𝘰𝘵𝘩𝘦𝘴𝘦𝘴 𝘷𝘪𝘳𝘵𝘶𝘢𝘭𝘭𝘺 𝘣𝘦𝘧𝘰𝘳𝘦 𝘳𝘶𝘯𝘯𝘪𝘯𝘨 𝘢𝘯𝘺 𝘦𝘹𝘱𝘦𝘳𝘪𝘮𝘦𝘯𝘵 𝘪𝘯 𝘵𝘩𝘦 𝘭𝘢𝘣? 𝗡𝗲𝘄 𝗽𝗿𝗲𝗽𝗿𝗶𝗻𝘁 𝗼𝘂𝘁 𝗻𝗼𝘄! 🎉 📄 Paper: doi.org/10.64898/202... 💻 Colab notebook: colab.research.google.com/drive/1k9411... 🗂️ Code: github.com/yongrong-qiu... (1/🧵)

𝗞𝗲𝘆 𝗳𝗶𝗻𝗱𝗶𝗻𝗴𝘀: - using GMMs we show that retinal inputs are functionally distinct & laminar-organized - functional diversity of retinal output matches with SC retinal input (using a VAE-approach and RGC reference data) - digital twin model generalizes across stimuli, which it wasn't trained on (3/🧵)

Excited to present at #NeurIPS this week on my work building biophysical models of the outer retina! If you’re around come check it out or just say hi, poster #2015, Friday 11-2🎉 You can find the full paper here: openreview.net/forum?id=ayj... In brief🧵:

The poster will be presented in Exhibit Hall C,D,E #2014 on Wednesday, 3 Dec 4:30 p.m. PST — 7:30 p.m. PST by @dgonschorek.bsky.social #neurips2025 #CompNeuro #NeuroAI #neurips

Excited to share that our paper got accepted @NeurIPS! 🎉 We introduce TRACE, a new contrastive learning method for visualizing multi-trial neural time-series data. 📊 2D visualizations revealing biological patterns 🔍 Automatic artifact detection 🔬 Works for calcium imaging & electrophysiology data