Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hidingby Jonggyu Jang, Hyeonsu…
Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamicsby Ruining Li, Chuanxia…
ReFeR: Improving Evaluation and Reasoning through Hierarchy of Modelsby Yaswanth Narsupalli, Abhranil Chandra, Sreevatsa Muppirala,…
Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Predictionby Yice Zhang, Jie Zeng, Weiming Hu,…
V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Databy Rotem Shalev-Arkushin, Aharon Azulay, Tavi Halperin, Eitan…
Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamicsby Weitong Zhang, Chengqi Zang, Liu…
Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensingby Sina…
GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functionsby Salvatore Esposito, Qingshan Xu, Kacper Kania, Charlie…
Learning Gaze-aware Compositional GANby Nerea Aranjuelo, Siyu Huang, Ignacio Arganda-Carreras, Luis Unzueta, Oihana Otaegui, Hanspeter…
Gradient Inversion of Federated Diffusion Modelsby Jiyue Huang, Chi Hong, Lydia Y. Chen, Stefanie RoosFirst…