arxiv:2504.20752
Roman Abramov
monsetrum
AI & ML interests
None yet
Recent Activity
authored
a paper
3 days ago
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop
Reasoning with Transformers
upvoted
a
paper
3 days ago
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement
Learning
Organizations
None yet
Papers
1
models
0
None public yet
datasets
0
None public yet