arxiv:2501.10799
Sainbayar Sukhbaatar
sainbar
AI & ML interests
None yet
Recent Activity
authored
a paper
about 14 hours ago
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary
Feedback
authored
a paper
about 2 months ago
Training Large Language Models to Reason in a Continuous Latent Space
authored
a paper
2 months ago
Adaptive Decoding via Latent Preference Optimization
Organizations
None yet
Papers
22
models
None public yet
datasets
None public yet