Home  | News

21.02.2025

Tiny logo
Teaser image to MCML at AAAI 2025

MCML at AAAI 2025

Ten Accepted Papers

39th Conference on Artificial Intelligence, Philadelphia, PA, USA, Feb 25-Mar 04, 2025

We are happy to announce that MCML researchers have contributed a total of 10 papers to AAAI 2025. Congrats to our researchers!

Main Track (10 papers)

H. Chen • D. Krompass • J. Gu • V. Tresp
FedPop: Federated Population-based Hyperparameter Tuning.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI

A. Davtyan • S. Sameni • B. Ommer • P. Favaro
CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI GitHub

X. Feng • Z. Jiang • T. Kaufmann • P. Xu • E. Hüllermeier • P. Weng • Y. Zhu
DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI

M. Gui • J. Schusterbauer • U. Prestel • P. Ma • D. Kotovenko • O. Grebenkova • S. A. Baumann • V. T. HuB. Ommer
DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. Oral Presentation. DOI

Z. Li • S. S. Cranganore • N. Youngblut • N. Kilbertus
Whole Genome Transformer for Gene Interaction Effects in Microbiome Habitat Specificity.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI

J. Lan • D. Frassinelli • B. Plank
Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI

P. Ma • L. Rietdorf • D. Kotovenko • V. T. HuB. Ommer
Does VLM Classification Benefit from LLM Description Semantics?
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. Invited talk. DOI

Y. Mu • M. Shahzad • X. Zhu
MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI

Y. Shen • Z. Zhuang • K. Yuan • M.-I. Nicolae • N. Navab • N. Padoy • M. Fritz
Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI

Y. Zhang • Z. Ma • Y. Ma • Z. Han • Y. Wu • V. Tresp
WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration.
AAAI 2025 - 39th Conference on Artificial Intelligence. Philadelphia, PA, USA, Feb 25-Mar 04, 2025. DOI

#research #top-tier-work #huellermeier #kilbertus #navab #ommer #plank #seidl #tresp #zhu
Subscribe to RSS News feed

Related

Link to

28.11.2025

MCML at NeurIPS 2025

MCML researchers are represented with 45 papers at NeurIPS 2025 (36 Main, and 9 Workshops).

Link to Seeing the Bigger Picture – One Detail at a Time

27.11.2025

Seeing the Bigger Picture – One Detail at a Time

FLAIR, introduced by Zeynep Akata’s group at CVPR 2025, brings fine-grained, text-guided detail recognition to vision-language models.

Link to Daniel Rückert Among the World’s Most Cited Researchers

25.11.2025

Daniel Rückert Among the World’s Most Cited Researchers

MCML Director Daniel Rückert is among the world’s most cited researchers for AI in healthcare, part of 17 TUM scientists recognized in 2025.

Link to Research Stay at Stanford University

24.11.2025

Research Stay at Stanford University

Kun Yuan spent two months at Stanford with the AI X-Change Program, advancing biomedical vision-language models and launching three joint projects.

Link to Zigzag Your Way to Faster, Smarter AI Image Generation

20.11.2025

Zigzag Your Way to Faster, Smarter AI Image Generation

ZigMa, introduced by Björn Ommer’s group at ECCV 24, improves high-res AI image and video generation with fast, memory-efficient zigzag scanning.

Back to Top