arxiv:2504.03624
Soumye Singhal
soumye
AI & ML interests
LLM Post-training
Recent Activity
authored
a paper
6 days ago
Reward-aware Preference Optimization: A Unified Mathematical Framework
for Model Alignment
authored
a paper
6 days ago
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer
Models
upvoted
a
paper
6 days ago
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer
Models
Organizations
