19.01.2026
MCML at AAAI 2026
17 Accepted Papers (12 Main, and 5 Workshops)
40th Conference on Artificial Intelligence, Singapore, Jan 20-27, 2026
We are happy to announce that MCML researchers have contributed a total of 17 papers to AAAI 2026: 12 Main, and 5 Workshop papers. Congrats to our researchers!
Main Track (12 papers)
Democratizing Writing Support with AI: Insights from One Year of Real-World Interactions with an Open-Access Writing Feedback Tool.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. GitHub
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. Preprint available. arXiv
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
Conformal Prediction for Multi-Source Detection on a Network.
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
HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
Conformable Convolution for Topologically Aware Learning of Complex Anatomical Structures.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv
HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction.
AAAI 2026 - 40th Conference on Artificial Intelligence. Singapore, Jan 20-27, 2026. To be published. Preprint available. arXiv GitHub
Workshops (5 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
How to realize efficient Spiking Neural Networks?
MATH4AI @AAAI 2026 - Workshop on Foretell of Future AI from Mathematical Foundation 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
Ecological Determinants of Antidepressants Prescriptions in England: Using Machine Learning for Causal Discovery.
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. URL
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. Preprint available. URL
Related
24.02.2026
Cosmology: Measuring the Expansion of the Universe With Cosmic Fireworks
Daniel Gruen leads LMU’s campaign on rare SN Winny to refine the Hubble constant and address the Hubble tension in cosmology.
19.02.2026
COSMOS – Teaching Vision-Language Models to Look Beyond the Obvious
Presented at CVPR 2025, COSMOS shows how smarter training helps VLMs learn from details and context, improving AI understanding without larger models.
13.02.2026
Digdeep Podcast: Will School Still Work When AI Becomes the New Classmate?
In the new episode of #digdeep Jochen Kuhn and Florian Karsten discuss AI at schools.