Search papers, labs, and topics across Lattice.
6
0
10
15
Frozen LLMs can autonomously achieve recursive self-improvement by learning and refining explicit, executable world models from interaction data.
Targeting evaluation compute at specific tail-sensitive transition kernels cuts policy CVaR estimation error by up to 76% compared to standard end-to-end rollouts.
Lean-based mathematical reasoning can be surprisingly unreliable, but this work shows how to selectively trust its judgments with provable risk bounds, paving the way for more robust automated math problem solving.
Stop wasting resources on ad-hoc experiments: Bayesian Optimization offers a principled, probability-driven framework to automate scientific discovery.
Forget heuristic knob-tuning: decoding algorithms are just regularized optimization problems hiding in plain sight.
