Search papers, labs, and topics across Lattice.
4
0
7
Static sample selection in reinforcement fine-tuning is a recipe for suboptimal updates鈥擠IEM adapts dynamically, leading to superior performance on reasoning tasks.
Optimizing data mixtures through gradient descent can drastically reduce training costs and improve model performance without the need for extensive simulations.
A 440MB multilingual translation model now rivals commercial APIs, opening the door for performant on-device translation.
