3 papers
cs.LG2026
Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning
Syeda Nahida Akter, Shrimai Prabhumoye, Matvei Novikov +8
Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL). While prior work has successfully applied RL…
cs.LG2025
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
Syeda Nahida Akter, Shrimai Prabhumoye, Eric Nyberg +4
The prevailing paradigm for enhancing the reasoning abilities of LLMs revolves around post-training on high-quality, reasoning-intensive data. While emerging literature suggests th…
cs.AI2025
MIND: Math Informed syNthetic Dialogues for Pretraining LLMs
Syeda Nahida Akter, Shrimai Prabhumoye, John Kamalu +5
The utility of synthetic data to enhance pretraining data quality and hence to improve downstream task accuracy has been widely explored in recent large language models (LLMs). Yet…