Search papers, labs, and topics across Lattice.
Affiliation:
4
0
8
0
Small models can now learn new skills without forgetting old ones, thanks to a novel distillation technique that leverages a larger model to guide the learning process.
TAIScore reveals that effective critique in AI generation hinges on the dynamic interplay between actor capabilities and targeted feedback, outperforming larger models in practical applications.
Directly generating financial forecasts as tokens can lead to substantial improvements in investment performance, with a Sharpe ratio boost from 1.428 to 1.529.
LLMs predict test outputs far more reliably when they can vote between running buggy code and "reasoning" over pseudocode.
