arxiv:2510.05921
Carel van Niekerk
CarelvNiekerk
AI & ML interests
Reinforcement Learning, Reasoning, Agentic RL, LLMs, Uncertainty Estimation, Active Learning
Recent Activity
authored
a paper
25 days ago
Text-to-SQL Task-oriented Dialogue Ontology Construction
authored
a paper
25 days ago
Post-Training Large Language Models via Reinforcement Learning from
Self-Feedback
authored
a paper
25 days ago
Less is More: Local Intrinsic Dimensions of Contextual Language Models
Organizations
models
0
None public yet
datasets
0
None public yet