MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training

A new framework called EntPruner has been introduced to address parameter redundancy in large-scale vision generative models, specifically diffusion and flow models. This framework employs an entropy-guided automatic progressive pruning strategy, which assesses the importance of model blocks based on Conditional Entropy Deviation (CED) to optimize performance across various downstream tasks.

PartDiffuser has been introduced as a novel semi-autoregressive diffusion framework aimed at improving the generation of 3D meshes from point clouds. This method enhances the balance between global structural consistency and local detail fidelity by employing a part-wise approach, utilizing semantic segmentation and a discrete diffusion process for high-frequency geometric feature reconstruction.

A new study introduces a plug-and-play memory system for Diffusion Transformer-based video generation models, specifically the DiT, enhancing their ability to incorporate world knowledge and improve visual coherence. This development addresses the models' frequent violations of physical laws and commonsense dynamics, which have been a significant limitation in their application.

The introduction of Self-Paced Group Relative Policy Optimization (GRPO) marks a significant advancement in reinforcement learning for video generation, allowing reward feedback to evolve alongside the generator. This method addresses limitations of static reward models, enhancing stability and effectiveness in generating high-quality video content.

A new inference pipeline named Jenga has been introduced to enhance the efficiency of video generation using Video Diffusion Transformer (DiT) models. This approach addresses the computational challenges associated with self-attention and the multi-step nature of diffusion models by employing dynamic attention carving and progressive resolution generation.