Instructors

Prof. Dr. Christian Wachinger, Tom Nuno Wolf, Fabian Bongratz, Bailiang Jian, Yitong Li, Emre Kavak

Contact

If you have any questions regarding this seminar contact seminars@ai-med.de.

Announcements

🏆Best blog posts from this semester:
Slides from the kickoff: ML-Neuro Seminar Summer 25_ Kickoff.pdf
The pre-course meeting is on Feb 3, 2025, at 1pm via Zoom. Zoom link: https://tum-conf.zoom-x.de/j/69292641936?pwd=Ko6lQGNx1A6ck5A96SywP2C6DGkbeN.1 Meeting ID: 692 9264 1936 Passcode: 960221
Slides from the pre-course meeting: ML-Neuro pre-course-1.pdf

Registration

Registration to the seminar is done via the TUM Matching Platform. Pay attention to the deadlines!!

Timeline

Feb 3, 2025, 1pm: pre-course meeting
April 30, 2025, 11am, Seminarraum Holbeinstrasse 11: Kickoff, assignment of papers (attendance is mandatory)
During the semester: meet your supervisor (optional but recommended)
July 3 & 4, 9am - 3pm, Seminarraum Holbeinstrasse 11: Block seminar (attendance is mandatory)

Topics

Paper ID	Title	Published in	Link	Group/Supervisor	Student	Additional Material
1	Toward expert-level medical question answering with large language models	Nature Medicine	https://www.nature.com/articles/s41591-024-03423-7	Bailiang	Julia Seidl
2	Towards accurate differential diagnosis with large language models	Nature Medicine	https://www.nature.com/articles/s41586-025-08869-4	Bailiang	Thanh Dang
3	Medical large language models are vulnerable to data-poisoning attacks	Nature Medicine	https://www.nature.com/articles/s41591-024-03445-1	Bailiang	Smail Smajlović
4	Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-Ray Expert Models	CVPR	https://arxiv.org/abs/2404.04936	Yitong	Melek Walha
5	MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models	ICLR	https://arxiv.org/abs/2410.13085	Yitong	Himel Gosh
6	Learning Causal Alignment for Reliable Disease Diagnosis	ICLR	https://arxiv.org/abs/2310.01766	Yitong	Simon Bohnen
7	CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense	NeurIPS	https://arxiv.org/abs/2410.23091	Emre
8	Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography	MICCAI	https://arxiv.org/abs/2405.12255	Emre	Timofey Kuznetsov
9	Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization	MICCAI	https://arxiv.org/abs/2407.02900	Emre	Clemens Schwarzmann
10	VoxelPrompt: A Vision-Language Agent for Grounded Medical Image Analysis	Arxiv	https://arxiv.org/abs/2410.08397	Nuno	Alexandra Marquardt
11	SynthSR: A public AI tool to turn heterogeneous clinical brain scans into high-resolution T1-weighted images for 3D morphometry	Science Advances	https://www.science.org/doi/10.1126/sciadv.add3607	Fabi	Katherina Terefenko
12	SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments	ICLR	https://openreview.net/forum?id=OJsMGsO6yn	Fabi	Paul Burkhardt
13	Learnable latent embeddings for joint behavioural and neural analysis	Nature	https://www.nature.com/articles/s41586-023-06031-6	Fabi	Vivien Hopf	https://cebra.ai/
14	A multimodal generative AI copilot for human pathology	Nature	https://www.nature.com/articles/s41586-024-07618-3	Nuno	Lara Lanz
15	ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image	ECCV	https://link.springer.com/chapter/10.1007/978-3-031-73661-2_12	Nuno	Hyunji Lee