Search papers, labs, and topics across Lattice.
5
0
8
Model-generated skills can actually hurt agent performance, and bigger models don't necessarily make for better skill extractors or consumers.
SkillOpt transforms agent skill development into a reproducible optimization process, achieving state-of-the-art results by treating skills as trainable parameters.
Train a text-to-image model that rivals the state-of-the-art with 1/5th the compute by using GPT-4 to generate better captions.
Hierarchical planning and self-reflection can finally wrangle AIGC tools into producing coherent, visually consistent webpages.
Today's best text-to-audio-video models may look and sound impressive, but they still struggle with basic physics, coherent speech, and even rendering text correctly.
