Generative AI Simulate Motion for Text-to-Video Generation (arXiv 2025) Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss Text-to-Video Evaluation on Dynamics (NeurIPS 2024) DEVIL - Evaluation of Text-to-Video Generation Models - A Dynamics Perspective Inserting Objects Using Simple Instructions (arXiv 2024) Add-SD Rational Image Generation without Manual Reference Large-Scale Pre-training Generic Pre-training with CLIP alignment (TMLR 2023) CAE v2 - Context Autoencoder with CLIP Latent Alignment Human-Centric Pre-training with Structure Prior (NeurIPS 2023) HAP - Structure-Aware Masked Image Modeling for Human-Centric Perception Human-Centric Pre-training with Text-To-Image Large-Scale Data (ICCV 2023) Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification
