Zhedong Zheng

Existing deepfake detectors fall apart when faced with realistic, multi-step editing pipelines, highlighting the need for methods that can trace the *history* of manipulations, not just detect a single forgery.

General-purpose vision-language models stumble when looking down from drones, but a new benchmark reveals that multi-task learning can substantially improve their aerial reasoning skills.

Achieve state-of-the-art video frame interpolation by making your diffusion model predict the past, not just the future.