Zilin Pan — accepted AI-conference papers

2026

Rethinking Video Generation Model for the Embodied World

Yufan Deng, Zilin Pan, Hongyu Zhang, Xiaojie Li, Huruoqing, Yufei Ding +3

ICML 2026poster

While video generation holds promise for embodied intelligence, current video models struggle with physical realism, and progress is hindered by the lack of standardized benchmarks. To address this gap, we introduce a comprehensive robotics benchmark, RBench, designed to evaluate robot-oriented vide…

Cited by 0 Source ↗Scholar ↗

2026

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation

Hongyu Zhang, Yufan Deng, Zilin Pan, Peng-Tao Jiang, Bo Li, Qibin Hou +3

ICLR 2026poster

Generating high-quality videos from complex temporal descriptions, which refer to prompts containing multiple sequential actions, remains a significant challenge. Existing methods are constrained by an inherent trade-off: using multiple short prompts fed sequentially into the model improves action f…

Cited by 0 Source ↗code ↗Scholar ↗