jkrs's picture

2 6

jkrs

jkrs

·

AI & ML interests

Reinforcement Learning

Recent Activity

upvoted a paper 17 days ago

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

upvoted a paper 6 months ago

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers

liked a dataset over 1 year ago

Anthropic/hh-rlhf

View all activity

Organizations

None yet

upvoted a paper 17 days ago

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

Paper • 2602.12579 • Published Feb 13 • 2

upvoted a paper 6 months ago

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers

Paper • 2510.00915 • Published Oct 1, 2025 • 2