Bo An

SEP 8, 2026 · PREPRINT

Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation

arXiv

A novel algorithmic approach to an unvalidated problem (test-time RL for code generation) demonstrated on benchmarks without peer review, showing promising technical results but lacking independent verification or clinical/practical implementation data.

SEP 3, 2026 · PREPRINT

Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs

arXiv

A novel machine-learning framework tested on coding benchmarks without peer review; demonstrates feasibility and initial results but requires independent validation and clinical or practical deployment evidence.

SEP 3, 2026 · PREPRINT

DE-Venus: A Data-Efficient RLVR Framework for Large Language Models

arXiv

This is a preprint describing a software framework and engineering approach with empirical results on benchmarks and proprietary business scenarios, but without peer review, clinical outcomes, or independent validation of the claimed efficiency gains.

AUG 10, 2026 · PREPRINT

VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting

arXiv

A novel machine-learning architecture for weather forecasting tested on a single benchmark dataset with no clinical or operational validation, peer review status unknown, and no comparison of forecast accuracy against operational meteorological standards or human forecasters.