Search papers, labs, and topics across Lattice.
2
0
2
13
Failure-driven post-training, combined with a meticulously curated 10M token STEM dataset, unlocks a 4.68% performance boost in LLM reasoning, proving that strategic data synthesis around model weaknesses is a powerful path to improvement.
An open-source ecosystem for agentic learning, complete with a trained agent and novel policy optimization, promises to accelerate research by providing a standardized, scalable platform.
