satiya-org

AI & ML interests

None defined yet.

Recent Activity

cjerzak  authored a paper about 18 hours ago

ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training

cjerzak  submitted a paper 2 months ago

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

cjerzak  authored a paper 2 months ago

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

View all activity

Team members 3