Tobias Gerstenberg
6 papers · 2022–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ Conference Polyglot (2) ๐ Cross-Pollinator (13) ๐บ๏ธ Taxonomy Completionist (15)
๐ฃ
Hot Topic Early Bird
Conferences
NIPS (5)
ICML (1)
Top co-authors
Keywords
benchmark evaluation
(2)
causal reasoning
(1)
model calibration
(1)
preference learning
(1)
self-supervised learning
(1)
text generation
(1)
multimodal learning
(1)
language model evaluation
(1)
confidence calibration
(1)
language model alignment
(1)
mutual information
(1)
preference modeling
(1)
language model
(1)
human-ai collaboration
(1)
constitutional alignment
(1)
iterative finetuning
(1)
agent behavior
(1)
theory of mind
(1)
commonsense reasoning
(1)
dialogue system
(1)
Papers
Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
ICML 2025
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
NIPS 2024
MARPLE: A Benchmark for Long-Horizon Inference
NIPS 2024
Understanding Social Reasoning in Language Models with Language Models
NIPS 2023
MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
NIPS 2023
Uncalibrated Models Can Improve Human-AI Collaboration
NIPS 2022