Search papers, labs, and topics across Lattice.
Peking University, Qiyuan Tech, Sumeru/Awesome-LLM-Reasoning
2
0
5
The organization of post-training reasoning data into a cohesive framework reveals crucial insights that could accelerate advancements in large reasoning models.
LLMs can be both faster and smarter: pre-learned reasoning skills cut down token usage while boosting accuracy on coding and math problems.
