A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse

Recent advancements in reward feedback learning (ReFL) highlight the effectiveness of video generation models as latent reward models, addressing significant challenges in aligning video generation with human preferences. Traditional video reward models have limitations due to their reliance on pixel-space inputs, which complicate the optimization process and increase memory usage.

A new study has introduced an innovative approach to image generation by incorporating intrinsic scene properties into diffusion models, addressing the issue of spatial inconsistency and distortion in generated images. This method co-generates images alongside their intrinsic properties, enhancing the model's understanding of scene structures.

A new method called DEMIST has been introduced for synthesizing quantitative magnetization transfer (qMT) maps, specifically pool size ratio (PSR) maps, from standard T1-weighted and FLAIR images using a 3D latent diffusion model. This approach utilizes a two-stage process involving separate autoencoders and a conditional diffusion model with decoupled conditioning mechanisms.

OmniRefiner has been introduced as a detail-aware refinement framework aimed at improving reference-guided image generation. This framework addresses the limitations of current diffusion models, which often fail to retain fine-grained visual details during image refinement due to inherent VAE-based latent compression issues. By employing a two-stage correction process, OmniRefiner enhances pixel-level consistency and structural fidelity in generated images.

Random Projection Flows (RPFs) have been introduced as a new framework for injective normalizing flows, utilizing random matrix theory and geometry to project data into lower-dimensional spaces. This method employs random semi-orthogonal matrices derived from Gaussian matrices, offering a more efficient and theoretically grounded approach compared to traditional PCA-based flows.

A new model called SPINRec has been introduced to enhance explanation fidelity in recommender systems, addressing the gap in accurately reflecting a model's reasoning. This model employs stochastic baseline sampling to generate personalized and stable explanations by integrating multiple user profiles from empirical data.

A new method for generating high-quality synthetic tabular data using Tensor Networks, specifically Matrix Product States (MPS), has been proposed. This approach addresses challenges related to data scarcity and privacy constraints in artificial intelligence by ensuring differential privacy through noise injection and gradient clipping during training.

The STCDiT framework has been introduced as a novel video super-resolution solution that utilizes a pre-trained video diffusion model to enhance video quality by restoring structural and temporal integrity from degraded inputs, particularly under complex camera movements. This method employs a motion-aware VAE reconstruction technique to achieve segment-wise reconstruction, ensuring uniform motion characteristics within each segment.