Search papers, labs, and topics across Lattice.
3
0
6
0
Signal processing offers a surprisingly effective lens for understanding and improving LoRA, the reigning champ of parameter-efficient fine-tuning.
Zeroth-order optimization stability depends on the *entire* Hessian spectrum, not just the largest eigenvalue like first-order methods, offering a new perspective on implicit regularization.
Stop wasting compute: a learned policy can intelligently allocate LLM inference budgets, boosting accuracy by up to 12.8% compared to uniform allocation.
