Zaiwen Wen

LMask: Learn to Solve Constrained Routing Problems with Lazy Masking

Learning the Quadratic Assignment Problem with Warm-Started MCMC Finetuning and Cross-Graph Attention

Reinforcement Learning for Heterogeneous DAG Scheduling with Weighted Cross-Attention

Accelerating Optimization via Differentiable Stopping Time

A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models

Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures

Tree-Based Premise Selection for Lean4

OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling

Retraction-free optimization over the Stiefel manifold with application to the LoRA fine-tuning