Search papers, labs, and topics across Lattice.
5
0
8
7
This work defines the scaling inflection point as the per-session budget where marginal Elo gains match the independent-sampling reference, and proposes Elo-per-token analysis, which tracks the best solution found at each token budget and uses a Bradley-Terry model to aggregate within-task orderings into Elo ratings across tasks with different score scales.
The hardest AI tasks remain largely unsolved, with current models achieving only a 2.6% success rate on economically valuable workflows.
Scaling prompt learning by 17x without sacrificing accuracy is now possible, unlocking efficient self-improvement for LLM agents.
Get 2x faster video generation from diffusion transformers without sacrificing quality, thanks to a clever parameter-free error compensation technique.
LLM-driven program evolution gets a smart upgrade: AdaEvolve dynamically allocates resources to promising solution candidates, leaving static schedules in the dust.
