arxiv:2503.11629
Stefan Lionar
slionar
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Rethinking the Trust Region in LLM Reinforcement Learning
upvoted
a
paper
4 months ago
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
upvoted
a
paper
4 months ago
Variational Reasoning for Language Models
Organizations
None yet
