Shayda Moezzi — accepted AI-conference papers

2026

MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis

Xiangyu Bai, He Liang, Bishoy Galoaa, Utsav Nandi, Shayda Moezzi, Yuhang He +1

CVPR 2026

While text-to-video (T2V) generation has achieved remarkable progress in photorealism, generating intent-aligned videos that faithfully obey physics principles remains a core challenge. In this work, we systematically study Newtonian motion-controlled text-to-video generation and evaluation, emphasi

Cited by 0 Source ↗code ↗Scholar ↗

2026

Position: Video LLMs Must Not Ignore the Pixel Dynamics in Plain Sight

Shayda Moezzi, Umer Saleem, Andong Deng, Chen Chen, Sarah Ostadabbas

ICML 2026poster

The essence of video lies in pixel dynamics: motion, state transitions, and the flow of visual information across frames. Video Large Language Models (LLMs) have rapidly become the dominant paradigm for video understanding in computer vision, sophisticated multimodal reasoning over complex, long-for…

Cited by 0 Source ↗Scholar ↗