Author

Zi-Tong Yu

h-index 4 View on Semantic Scholar

We have 4 of 24 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 Sep 2026

Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models

World Action Models (WAMs) extend Vision-Language-Action (VLA) models by incorporating future visual dynamics into action generation. However, existing WAMs often utilize imagined futures with limited adaptation to evolving execution progress, potentially introducing distracting or unreliable predictive cues. This limi...

Yi-Jie Zhu, Zi-Tong Yu, Wei Li et al. · 0 citations

Jul 2026

PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models

This approach substantially reduces the computation of long-context modeling, while enhancing the performance of the baseline model, achieving a speedup of 1.8$\times to 2.5$\times compared to the baseline VLLM.

Zihan Song, Shuo Ye, Bo Zhao et al. · arXiv.org · 0 citations

Jul 2026

GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs

This work proposes GMoT, a Gated Motion-Aware Tokenization module that explicitly distills sparse kinematic evidence into a compact sequence prior to temporal modeling, and introduces Body-Region Grounding (BRG) Recall as an anatomical-grounding proxy conditioned on correct predictions.

Taorui Wang, Wei Xia, Hui Ma et al. · arXiv.org · 0 citations

Jul 2026

AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning

AC-VLA is introduced, a plug-and-play Action Compositional learning framework comprising two architecture-agnostic components that achieves a ~28% absolute improvement on compositional OOD tasks while maintaining near-perfect in-distribution performance.

Xiaojiang Peng, Kai Peng, Jie Lu et al. · arXiv.org · 2 citations