Pre-NeurIPS 2025

Twice a year, we host a Pre-Conference Poster Session at IMBIT.

These sessions provide an excellent opportunity for the AI community across Freiburg to present their research and connect with fellow researchers.

While the sessions primarily feature posters of papers accepted to upcoming conferences, they also welcome recently peer-reviewed work from other conferences, workshops, and journals. In addition, the sessions serve as a valuable networking opportunity for local start-ups and companies to engage in discussions about the latest advancements in AI research at Freiburg University.

Food, snacks, and beverages will be provided for all registered attendees.

List of Posters that will be presented:

1. Hindel J, Mekic E, Naga Karthik E, Mohan R, Cattaneo D, Kalweit M, Valada A, 2025. Dynamic Robot-Assisted Surgery with Hierarchical Class-Incremental Semantic Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention – Advanced Machine Learning for Medical Imaging (MICCAI AMAI 2025). DOI: https://arxiv.org/abs/2508.01713
2. Werby A, Büchner M, Röfer A, Huang C, Burgard W, Valada A, 2025. Articulated Object Estimation in the Wild. Conference on Robot Learning (CoRL 2025). DOI: https://arxiv.org/abs/2509.01708
3. Kassab C, Morin S, Büchner M, Mattamala M, Gupta K, Valada A, Paull L, Fallon M, 2025. OpenLex3D: A New Evaluation Benchmark for Open-Vocabulary 3D Scene Representations. Conference on Neural Information Processing Systems (NeurIPS 2025). DOI: https://arxiv.org/abs/2503.19764
4. Mousakhan A, Mittal S, Galesso S, Farid K, Brox T, 2025. Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models. Conference on Neural Information Processing Systems (NeurIPS 2025). DOI: https://arxiv.org/abs/2507.13162
5. Naouar M, Vogt Y, Boedecker J, Kalweit G, Kalweit M, 2025. One For All: A Unified Approach to Classification and Self-Explanation. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2025). DOI: https://papers.miccai.org/miccai-2025/paper/4655_paper.pdf
6. Pfefferle A, Hog J, Purucker L, Hutter F, 2025. nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN. European Conference on Neural Information Processing Systems – AI for Tabular Data Workshop (EurIPS 2025). DOI: https://arxiv.org/abs/2511.03634
7. Erickson N, Purucker L, Tschalzev A, Holzmüller D, Mutalik Desai P, Salinas D, Hutter F, 2025. TabArena: A Living Benchmark for Machine Learning on Tabular Data.
   Conference on Neural Information Processing Systems (NeurIPS 2025). DOI: https://arxiv.org/abs/2506.16791
8. Zehle T, Schlager M, Heiß T, Feurer M, 2025. CAPO: Cost-Aware Prompt Optimization. International Conference on Automated Machine Learning (AutoML 2025). DOI: https://openreview.net/forum?id=UweaRrg9D0
9. Ging S, Walter S, Bratulić J, Dienert J, Bast H, Brox T, 2025. Using Knowledge Graphs to Harvest Datasets for Efficient CLIP Model Training. German Conference on Pattern Recognition (GCPR 2025). DOI: https://arxiv.org/abs/2505.02746
10. Bratulić J, Mittal S, Hoffmann DT, Boehm S, Schirrmeister RT, Ball T, Rupprecht C, Brox T, 2025. Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling. German Conference on Pattern Recognition (GCPR 2025). DOI: https://arxiv.org/abs/2501.06256
11. Robertson J, Reuter A, Guo S, Hollmann N, Hutter F, Schölkopf B, 2025. Do-PFN: In-Context Learning for Causal Effect Estimation. Conference on Neural Information Processing Systems / European Conference on Neural Information Processing Systems (NeurIPS/EurIPS 2025).
12. Bühler M, Purucker L, Hutter F, 2025. Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models. European Conference on Neural Information Processing Systems – AI for Tabular Data Workshop (EurIPS 2025). DOI: https://openreview.net/forum?id=EfQv02muYG&noteId=EfQv02muYG
13. Das I, Safari M, Adriaensen S, Hutter F, 2025. Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics. Conference on Neural Information Processing Systems (NeurIPS 2025). DOI: https://arxiv.org/abs/2502.03654