
Xindi Wu
@cindy_x_wu • 5,012 subscribers
PhD student @PrincetonCS | Data-centric multimodal ml | prev @roboVisionCMU @CMU_Robotics | @NVIDIAAI @RealityLabs @Snapchat
Videos

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10
Xindi Wu110,281 Aufrufe • vor 4 Monaten
Keine weiteren Inhalte verfügbar