Michael Kirchhof

According to our database, Michael Kirchhof authored at least 24 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Uncertainty Quantification for LLM Function-Calling.

Zihuiwen Ye, Lukas Aichberger, Michael Kirchhof, Sinead Williamson, Luca Zappella, Yarin Gal, Arno Blaas, Adam Golinski

CoRR, April, 2026

LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss.

Szilvia Ujváry, Louis Béthune, Pierre Ablin, João Monteiro, Marco Cuturi, Michael Kirchhof

CoRR, February, 2026

2025

Learning Unmasking Policies for Diffusion Language Models.

Metod Jazbec, Theo X. Olausson, Louis Béthune, Pierre Ablin, Michael Kirchhof, João Monteiro, Victor Turrisi, Jason Ramapuram, Marco Cuturi

CoRR, December, 2025

Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs.

Preetum Nakkiran, Arwen Bradley, Adam Golinski, Eugène Ndiaye, Michael Kirchhof, Sinead Williamson

CoRR, November, 2025

Pretraining with hierarchical memories: separating long-tail and common knowledge.

Hadi Pouransari, David Grangier, C. Thomas, Michael Kirchhof, Oncel Tuzel

CoRR, October, 2025

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design.

Deepro Choudhury, Sinead Williamson, Adam Golinski, Ning Miao, Freddie Bickford Smith, Michael Kirchhof, Yizhe Zhang, Tom Rainforth

CoRR, August, 2025

The Geometries of Truth Are Orthogonal Across Tasks.

Waïss Azizian, Michael Kirchhof, Eugène Ndiaye, Louis Béthune, Michal Klein, Pierre Ablin, Marco Cuturi

CoRR, June, 2025

Self-reflective Uncertainties: Do LLMs Know Their Internal Answer Distribution?

Michael Kirchhof, Luca Füger, Adam Golinski, Eeshan Gunesh Dhekane, Arno Blaas, Sinead Williamson

CoRR, May, 2025

Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency.

Michael Kirchhof, James Thornton, Louis Béthune, Pierre Ablin, Eugène Ndiaye, Marco Cuturi

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents.

Michael Kirchhof, Gjergji Kasneci, Enkelejda Kasneci

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results.

Andrea Santilli, Adam Golinski, Michael Kirchhof, Federico Danieli, Arno Blaas, Miao Xiong, Luca Zappella, Sinead Williamson

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025

2024

Uncertainties of Latent Representations in Computer Vision

Michael Kirchhof

PhD thesis, 2024

Sparse Repellency for Shielded Generation in Text-to-image Diffusion Models.

Michael Kirchhof, James Thornton, Pierre Ablin, Louis Béthune, Eugène Ndiaye, Marco Cuturi

CoRR, 2024

Uncertainties of Latent Representations in Computer Vision.

Michael Kirchhof

CoRR, 2024

Pretrained Visual Uncertainties.

Michael Kirchhof, Mark Collier, Seong Joon Oh, Enkelejda Kasneci

CoRR, 2024

Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks.

Bálint Mucsányi, Michael Kirchhof, Seong Joon Oh

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Trustworthy Machine Learning.

Bálint Mucsányi, Michael Kirchhof, Elisa Nguyen, Alexander Rubinstein, Seong Joon Oh

CoRR, 2023

When are post-hoc conceptual explanations identifiable?

Tobias Leemann, Michael Kirchhof, Yao Rong, Enkelejda Kasneci, Gjergji Kasneci

Proceedings of the Uncertainty in Artificial Intelligence, 2023

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates.

Michael Kirchhof, Bálint Mucsányi, Seong Joon Oh, Enkelejda Kasneci

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs.

Michael Kirchhof, Enkelejda Kasneci, Seong Joon Oh

Proceedings of the International Conference on Machine Learning, 2023

2022

Disentangling Embedding Spaces with Minimal Distributional Assumptions.

Tobias Leemann, Michael Kirchhof, Yao Rong, Enkelejda Kasneci, Gjergji Kasneci

CoRR, 2022

A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning.

Michael Kirchhof, Karsten Roth, Zeynep Akata, Enkelejda Kasneci

Proceedings of the Computer Vision - ECCV 2022, 2022

2021

pRSL: Interpretable multi-label stacking by learning probabilistic rules.

Michael Kirchhof, Lena Schmid, Christopher Reining, Michael ten Hompel, Markus Pauly

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Chances of Interpretable Transfer Learning for Human Activity Recognition in Warehousing.

Michael Kirchhof, Lena Schmid, Christopher Reining, Michael ten Hompel, Markus Pauly

Proceedings of the Computational Logistics - 12th International Conference, 2021