Michael Kirchhof
9 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) 🗺️ Taxonomy Completionist (12)
🔥
Unstoppable
(5)
❓
The Questioner
Conferences
ICML (3)
NIPS (2)
UAI (2)
ACL (1)
ECCV (1)
Top co-authors
Keywords
uncertainty quantification
(3)
aleatoric uncertainty
(2)
zero-shot learning
(2)
transfer learning
(1)
independent component analysis
(1)
principal component analysis
(1)
bayesian inference
(1)
embedding space
(1)
belief propagation
(1)
multi-label classification
(1)
posterior distribution
(1)
rule learning
(1)
probabilistic model
(1)
latent variable
(1)
language model
(1)
out-of-distribution detection
(1)
interpretable model
(1)
pretrained model
(1)
concept discovery
(1)
post-hoc explanation
(1)
Papers
Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
ICML 2025
Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results
ACL 2025
Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents
ICML 2025
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
NIPS 2024
When are post-hoc conceptual explanations identifiable?
UAI 2023
Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
ICML 2023
URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
NIPS 2023
A Non-Isotropic Probabilistic Take On Proxy-Based Deep Metric Learning
ECCV 2022
pRSL: Interpretable multi-label stacking by learning probabilistic rules
UAI 2021