Author

Si-Yu Zhu

h-index 7 View on Semantic Scholar

We have 3 of 15 papers

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 Oct 2026

MemWM: Associative Memory-Enhanced Latent World Models for Long-Horizon Planning

World models trained via latent dynamics offer a scalable path for embodied planning, yet existing methods suffer from representational collapse, computational overhead, and limited long-horizon capability. We introduce MemWM, a memory-enhanced latent world model that augments JEPA-style prediction with a content-addre...

Yu-Wei Sun, Si-Yu Zhu · 0 citations

#machine learning Preprint Oct 2026

Enhancing Latent World Models with Associative Memory

A memory-enhanced latent world model that augments JEPA-style prediction with a content-addressable memory bank is introduced that achieves state-of-the-art performance with a lightweight architecture, outperforming conventional latent world models on long-horizon planning tasks.

Yu-Wei Sun, Si-Yu Zhu · 0 citations

Jul 2026

Glob3R: Global Structure-from-Motion with 3D Foundation Models

Glob3R is presented, a global SfM-style reconstruction built on 3D foundation models to explicitly optimize feed-forward geometric predictions, and consistently improves over feed-forward foundation-model baselines and recent scalable reconstruction methods, while being more robust than classical SfM pipelines.

Junyuan Deng, Heng Li, Ke-Jie Qiu et al. · arXiv.org · 0 citations