PhD student, The Chinese University of Hong Kong
2 papers at NeurIPS 2025
We present ShotBench, a new benchmark for evaluating VLMs' cinematography understanding, along with the ShotQA dataset and our ShotVL model, which achieves state-of-the-art performance over both strong open-source and proprietary baselines.
Imagine360 creates high-quality, immersive 360 videos from perspective video anchors.