Simon Schrodi (@simonschrodi) 's Twitter Profile
Simon Schrodi

@simonschrodi

🎓 PhD student in interpretability @UniFreiburg @CVisionFreiburg 💡 interested in mechanistic interpretability, robustness, AutoML & ML for climate science

ID: 3609623715

linkhttps://simonschrodi.github.io/ calendar_today10-09-2015 13:26:42

34 Tweet

79 Takipçi

140 Takip Edilen

Frank Hutter (@frankrhutter) 's Twitter Profile Photo

I'm at #NeurIPS2023 with my amazing team, excited to be presenting 6 papers at the main track and 2 at workshops, as well as a keynote in the table representation learning workshop. Here's all the info in one tweet, ordered by day. Please come by and chat with us 🙂 Tuesday

Julien Siems (@julien_siems) 's Twitter Profile Photo

1/4 Excited for our new work showing that Mamba can perform in-context learning on simple function classes and NLP tasks. (Riccardo Grazzi, Simon Schrodi, Thomas Brox, Frank Hutter) Paper link: arxiv.org/abs/2402.03170  🧵👇

María A. Bravo (@mariaalebravo) 's Twitter Profile Photo

Excited to share that our paper, "Open-Ended VQA Benchmarking of Vision-Language Models by Exploiting Classification Datasets and Their Semantic Hierarchy," has been selected as a Spotlight at #ICLR2024! #AI #VLMs Paper: arxiv.org/pdf/2402.07270… Code: github.com/lmb-freiburg/o… 1/n

Excited to share that our paper, "Open-Ended VQA Benchmarking of Vision-Language Models by Exploiting Classification Datasets and Their Semantic Hierarchy," has been selected as a Spotlight at #ICLR2024! #AI #VLMs 
Paper: arxiv.org/pdf/2402.07270… 
Code: github.com/lmb-freiburg/o…
1/n
Philipp Schröppel (@philschroeppel) 's Twitter Profile Photo

📢 Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation #CVPR2024 We apply diffusion to a neural point cloud representation. It disentangles shape and appearance, which allows to generate both of them individually. Page: neural-point-cloud-diffusion.github.io

Andreas Christen (@envmet) 's Twitter Profile Photo

Can artificial intelligence assist climate adaptation in cities? Our collaborative Universität Freiburg and Fraunhofer-Gesellschaft project 'I4C' developed hyper-local deep-learning models to map and reduce heat across entire cities in support of urban planning in @Freiburg kommunikation.uni-freiburg.de/pm-en/press-re…

Can artificial intelligence assist climate adaptation in cities? Our collaborative <a href="/UniFreiburg/">Universität Freiburg</a> and <a href="/Fraunhofer/">Fraunhofer-Gesellschaft</a> project 'I4C' developed hyper-local deep-learning models to map and reduce heat across entire cities in support of urban planning in @Freiburg kommunikation.uni-freiburg.de/pm-en/press-re…
Julien Siems (@julien_siems) 's Twitter Profile Photo

1/9 There is a fundamental tradeoff between parallelizability and expressivity of Large Language Models. We propose a new linear RNN architecture, DeltaProduct, that can effectively navigate this tradeoff. Here's how!

1/9 There is a fundamental tradeoff between parallelizability and expressivity of Large Language Models. We propose a new linear RNN architecture, DeltaProduct, that can effectively navigate this tradeoff. Here's how!
Simon Schrodi (@simonschrodi) 's Twitter Profile Photo

Excited that our joint work was accepted as an Oral at #ICLR2025 🥳 Great collab with David Hoffmann! Check out his thread below for more details 👇 See you in Singapore 🇸🇬

Paul Gavrikov @ ICLR (@paulgavrikov) 's Twitter Profile Photo

On Thursday, I'll be presenting our paper "Can We Talk Models Into Seeing the World Differently?" at ICLR 2025 in Singapore! If you're attending or just around Singapore, l'd love to connect—feel free to reach out! Also, I’m exploring postdoc or industry opportunities–happy to

On Thursday, I'll be presenting our paper "Can We Talk Models Into Seeing the World Differently?" at ICLR 2025 in Singapore! If you're attending or just around Singapore, l'd love to connect—feel free to reach out! Also, I’m exploring postdoc or industry opportunities–happy to