Kasia Kobalczyk
4 papers · 2025–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
large language model
(3)
question generation
(1)
bayesian experimental design
(1)
offline learning
(1)
generalization
(1)
information gain
(1)
inductive bia
(1)
autonomous agent
(1)
human value
(1)
preference data
(1)
knowledge integration
(1)
neural process
(1)
conditional meta-learning
(1)
task disambiguation
(1)
reward modelling
(1)
informed meta-learning
(1)
robust generalisation
(1)
language-conditioned policies
(1)
causal inference
(1)
symbolic environments
(1)
Papers
Active Task Disambiguation with LLMs
ICLR 2025
Preference Learning for AI Alignment: a Causal Perspective
ICML 2025
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
ICML 2025
Towards Automated Knowledge Integration From Human-Interpretable Representations
ICLR 2025