19.01.2026
Nine Accepted Papers (6 Main, and 3 Workshops)
40th Conference on Artificial Intelligence, Singapore, Jan 20-27, 2026
We are happy to announce that MCML researchers have contributed a total of 9 papers to AAAI 2026: 6 Main, and 3 Workshop papers. Congrats to our researchers!
Main Track (6 papers)
AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
Statistical Learning Theory for Distributional Classification.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published.
Uncertainty Quantification for Machine Learning: One Size Does Not Fit All.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
Do Large Language Models Think Like the Brain? Sentence-Level Evidence from fMRI and Hierarchical Embeddings.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
Shapley Value Approximation Based on k-Additive Games.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
Fine-Grained Uncertainty Decomposition in Large Language Models: A Spectral Approach.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
Workshops (3 papers)
Towards Quantifying Incompatibilities in Evaluation Metrics for Feature Attributions.
XAI4Science @AAAI 2026 - 2nd Workshop XAI4Science: From Understanding Model Behavior to Discovering New Scientific Knowledge at the 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. URL
Towards Unified Vision Language Models for Forest Ecological Analysis in Earth Observation.
AI4ES @AAAI 2026 - Workshop on AI for Environmental Science at the 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv GitHub
WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents.
LaMAS @AAAI 2026 - Workshop on LLM-based Multi-Agent Systems: Towards Responsible, Reliable, and Scalable Agentic Systems at the 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published.
Related
15.01.2026
Blind Matching – Aligning Images and Text Without Training or Labels
CVPR 2025 research from Daniel Cremers’ group shows how images and text can be aligned without training data, labels, or paired examples.
08.01.2026
High-Res Images, Less Wait: A Simple Flow for Image Generation
ECCV 2024 research led by Björn Ommer’s team enables faster high-resolution image generation by boosting diffusion models with flow matching.
©Joachim Wendler - stock-adobe.com
02.01.2026
MCML Researchers in Highly-Ranked Journals
We are excited to announce that MCML researchers have four papers published in highly-ranked journals in 2026.
28.12.2025
Konstantin Riedl Wins Doctoral Award From the Friends of TUM E.V.
Former MCML member Konstantin Riedl receives the Doctoral Award of the Friends of TUM e.V. for his outstanding PhD dissertation.
