Andreas Kirsch
8 papers · 2019–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) π Academic Marathon (6) πΊοΈ Taxonomy Completionist (20)
π
Cross-Pollinator
(8)
π
Renaissance Researcher
(5)
π₯
Unstoppable
(5)
Conferences
NIPS (3)
AISTATS (2)
CVPR (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
bayesian active learning
(3)
data selection
(2)
uncertainty quantification
(2)
domain adaptation
(1)
bayesian inference
(1)
curriculum learning
(1)
epistemic uncertainty
(1)
language modeling
(1)
mutual information
(1)
feature space
(1)
greedy algorithm
(1)
information gain
(1)
acquisition function
(1)
empirical baye
(1)
out-of-distribution detection
(1)
training acceleration
(1)
treatment effect
(1)
aleatoric uncertainty
(1)
observational datum
(1)
predictive performance
(1)
Papers
Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs
ICLR 2025
All models are wrong, some are useful: Model Selection with Limited Labels
AISTATS 2025
CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
NIPS 2024
Deep Deterministic Uncertainty: A New Simple Baseline
CVPR 2023
Prediction-Oriented Bayesian Active Learning
AISTATS 2023
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt
ICML 2022
Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
NIPS 2021
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
NIPS 2019