Search papers, labs, and topics across Lattice.
2
3
7
4
Upcycling MoE models can achieve the same performance as larger fixed-size models while cutting GPU costs by 32%.
Free-form Chain-of-Thought prompting actually *hurts* LLMs when it comes to structured function-calling tasks, but a guided-structured template approach boosts tool-use accuracy by up to 12%.
