Michael Kirchhof

30 papers A* 4A 2Journal 19Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss. CoRR Szilvia Ujváry, Louis Béthune, Pierre Ablin, João Monteiro, Marco Cuturi, Michael Kirchhof
2025	J	`jnl`	BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design. CoRR Deepro Choudhury, Sinead Williamson, Adam Golinski, Ning Miao, Freddie Bickford Smith, Michael Kirchhof, Yizhe Zhang, Tom Rainforth
2025	J	`jnl`	Learning Unmasking Policies for Diffusion Language Models. CoRR Metod Jazbec, Theo X. Olausson, Louis Béthune, Pierre Ablin, Michael Kirchhof, João Monteiro, Victor Turrisi, Jason Ramapuram, Marco Cuturi
2025	—	`conf`	Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents. ICML (Position Papers) Michael Kirchhof, Gjergji Kasneci, Enkelejda Kasneci
2025	J	`jnl`	Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents. CoRR Michael Kirchhof, Gjergji Kasneci, Enkelejda Kasneci
2025	J	`jnl`	Pretraining with hierarchical memories: separating long-tail and common knowledge. CoRR Hadi Pouransari, David Grangier, C. Thomas, Michael Kirchhof, Oncel Tuzel
2025	—	`conf`	Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results. ACL (2) Andrea Santilli, Adam Golinski, Michael Kirchhof, Federico Danieli, Arno Blaas, Miao Xiong, Luca Zappella, Sinead Williamson
2025	J	`jnl`	Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results. CoRR Andrea Santilli, Adam Golinski, Michael Kirchhof, Federico Danieli, Arno Blaas, Miao Xiong, Luca Zappella, Sinead Williamson
2025	J	`jnl`	Self-reflective Uncertainties: Do LLMs Know Their Internal Answer Distribution? CoRR Michael Kirchhof, Luca Füger, Adam Golinski, Eeshan Gunesh Dhekane, Arno Blaas, Sinead Williamson
2025	A*	`conf`	Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency. ICML Michael Kirchhof, James Thornton, Louis Béthune, Pierre Ablin, Eugène Ndiaye, Marco Cuturi
2025	J	`jnl`	The Geometries of Truth Are Orthogonal Across Tasks. CoRR Waïss Azizian, Michael Kirchhof, Eugène Ndiaye, Louis Béthune, Michal Klein, Pierre Ablin, Marco Cuturi
2025	J	`jnl`	Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs. CoRR Preetum Nakkiran, Arwen Bradley, Adam Golinski, Eugène Ndiaye, Michael Kirchhof, Sinead Williamson
2024	A*	`conf`	Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks. NeurIPS Bálint Mucsányi, Michael Kirchhof, Seong Joon Oh
2024	J	`jnl`	Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks. CoRR Bálint Mucsányi, Michael Kirchhof, Seong Joon Oh
2024	J	`jnl`	Pretrained Visual Uncertainties. CoRR Michael Kirchhof, Mark Collier, Seong Joon Oh, Enkelejda Kasneci
2024	J	`jnl`	Sparse Repellency for Shielded Generation in Text-to-image Diffusion Models. CoRR Michael Kirchhof, James Thornton, Pierre Ablin, Louis Béthune, Eugène Ndiaye, Marco Cuturi
2024	—	`—`	Uncertainties of Latent Representations in Computer Vision Michael Kirchhof
2024	J	`jnl`	Uncertainties of Latent Representations in Computer Vision. CoRR Michael Kirchhof
2023	A*	`conf`	Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs. ICML Michael Kirchhof, Enkelejda Kasneci, Seong Joon Oh
2023	J	`jnl`	Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs. CoRR Michael Kirchhof, Enkelejda Kasneci, Seong Joon Oh
2023	J	`jnl`	Trustworthy Machine Learning. CoRR Bálint Mucsányi, Michael Kirchhof, Elisa Nguyen, Alexander Rubinstein, Seong Joon Oh
2023	A*	`conf`	URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates. NeurIPS Michael Kirchhof, Bálint Mucsányi, Seong Joon Oh, Enkelejda Kasneci
2023	J	`jnl`	URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates. CoRR Michael Kirchhof, Bálint Mucsányi, Seong Joon Oh, Enkelejda Kasneci
2023	A	`conf`	When are post-hoc conceptual explanations identifiable? UAI Tobias Leemann, Michael Kirchhof, Yao Rong, Enkelejda Kasneci, Gjergji Kasneci
2022	—	`conf`	A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning. ECCV (26) Michael Kirchhof, Karsten Roth, Zeynep Akata, Enkelejda Kasneci
2022	J	`jnl`	A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning. CoRR Michael Kirchhof, Karsten Roth, Zeynep Akata, Enkelejda Kasneci
2022	J	`jnl`	Disentangling Embedding Spaces with Minimal Distributional Assumptions. CoRR Tobias Leemann, Michael Kirchhof, Yao Rong, Enkelejda Kasneci, Gjergji Kasneci
2021	—	`conf`	Chances of Interpretable Transfer Learning for Human Activity Recognition in Warehousing. ICCL Michael Kirchhof, Lena Schmid, Christopher Reining, Michael ten Hompel, Markus Pauly
2021	J	`jnl`	pRSL: Interpretable Multi-label Stacking by Learning Probabilistic Rules. CoRR Michael Kirchhof, Lena Schmid, Christopher Reining, Michael ten Hompel, Markus Pauly
2021	A	`conf`	pRSL: Interpretable multi-label stacking by learning probabilistic rules. UAI Michael Kirchhof, Lena Schmid, Christopher Reining, Michael ten Hompel, Markus Pauly