Search papers, labs, and topics across Lattice.
2
0
4
An LLM-based agent achieves 18.3% out-of-sample returns in stock options trading by learning to select structured strategies, but surprisingly, retaining news during RL training halves performance.
Unlocking preference representation from noisy latents, PRISM achieves state-of-the-art accuracy while drastically reducing computational costs in video generation.
