Skip to content

Author

Siyin Wang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning

The World Critic Model is proposed, built on a lightweight LeJEPA architecture; WCM jointly predicts future latent state and estimates values, such that the critic's representation is explicitly trained to capture temporal dynamics rather than merely regress scalar returns.

Senyu Fei, Xiaopeng Yu, Siyin Wang et al. · 0 citations
Preprint Jul 2026

HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action Control

HiMe is proposed, a Hierarchical Embodied Memory framework that decouples embodied intelligence into a high-frequency Executor for execution, a Sentry for working memory, and a Planner for long-term strategy, and introduces a dynamic knowledge system based on cross-modal semantic schemas and active management mechanisms.

Li Ji, Siyin Wang, Pengfang Qian et al. · 1 citation