2 citations · 2 across the 5 of their papers we have counts for
5 papers
WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling
Zhongzheng Li, Qingsong Ran, Shikun Feng +5
Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suffer from poor sample efficienc…
On computation of unramified cohomology over non-closed fields
Wenhao Li
We give examples of varieties defined over a non-algebraically closed field with nontrivial unramified cohomology, in the case when the field is of bounded cohomologica…
OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining
Zhongzheng Li, Tiancan Feng, Wenhao Li +5
Designing optimizers for modern deep learning remains a challenging scientific problem, requiring the joint consideration of optimization geometry, state dynamics, numerical stabil…
Degree 2 del Pezzo surface bundles and stable rationality
Wenhao Li
We study the arithmetic of del Pezzo surfaces of degree 2 over a function field, and in particular, the cokernel of the homomorphism from the Picard group to the Galois-invaria…
ExLLM: Experience-Enhanced LLM Optimization for Molecular Design and Beyond
Nian Ran, Yue Wang, Xiaoyuan Zhang +4
Molecular design involves an enormous and irregular search space, where traditional optimizers such as Bayesian optimization, genetic algorithms, and generative models struggle to…