Ran He

SEP 8, 2026 · PREPRINT

To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models

arXiv

This is an early-stage methodological study proposing a novel problem formulation and baseline approach, without peer review, comparative validation against established methods, or clinical application.

SEP 6, 2026 · PREPRINT

One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control

arXiv

This is a methodological contribution from an unreviewed preprint proposing a novel algorithmic approach (OSOL) to a technical problem in multi-domain RL training, demonstrated on one model with controlled experiments but lacking peer review and clinical or real-world validation.