collaborators

9 papers

cs.SE2026

AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation

Xinyuan Song, Zekun Cai, Liang Zhao

High pass rates on established programming benchmarks such as HumanEval and LiveCodeBench do not always show whether a model can reason about algorithms. Many fixed benchmarks even…

cs.AI2026

AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills

Xinyuan Song, Zekun Cai, Liang Zhao

Designing an algorithm from a natural-language problem statement requires identifying the problem structure, reading constraints, choosing a suitable paradigm, checking correctness…

cs.SE2026

When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs

Xinyuan Song, Zekun Cai, Liang Zhao

Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control. We study this risk in code LLMs, wh…

cs.LG2026

LUMINA: A Grid Foundation Model for Benchmarking AC Optimal Power Flow Surrogate Learning

Hongwei Jin, Keunju Song, Zeeshan Memon +5

AC optimal power flow (ACOPF) is foundational yet computationally expensive in power grid operations, driving learning-based surrogates for large-scale grid analysis. These surroga…

cs.LG2026

Towards Systematic Generalization for Power Grid Optimization Problems

Zeeshan Memon, Yijiang Li, Hongwei Jin +2

AC Optimal Power Flow (ACOPF) and Security-Constrained Unit Commitment (SCUC) are fundamental optimization problems in power system operations. ACOPF serves as the physical backbon…

cs.LG2025

Structural Disentanglement of Causal and Correlated Concepts

Qilong Zhao, Shiyu Wang, Zeeshan Memon +5

Controllable data generation aims to synthesize data by specifying values for target concepts. Achieving this reliably requires modeling the underlying generative factors and their…