A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
MoCoGAN proposes a novel framework that decomposes video generation into motion and content subspaces, enabling effective video synthesis with a recurrent neural network in the motion part.
Unknown
Show-1 introduces a hybrid text-to-video generation framework that combines pixel-based and latent diffusion models to leverage their complementary strengths.
Unknown
Controlvideo introduces a training-free framework for controllable text-to-video generation by leveraging pre-trained text-to-image models.
Unknown
This paper introduces discrete flow matching, a novel framework that extends continuous flow matching to discrete data domains such as text and categorical variables.
Unknown
This paper proposes a representation alignment framework for diffusion transformers that improves generation performance by focusing on learning high-quality representations.
Unknown
This survey provides a comprehensive overview of efficient diffusion models, covering acceleration techniques, architectural optimizations, and specialized frameworks.
Unknown
Introduces Variational Diffusion Models (VDM), a framework that improves diffusion models by optimizing a variational lower bound, enabling competitive likelihoods and high-quality generation.
Unknown
This paper introduces FLASH, a fast and robust framework for privacy-preserving machine learning, focusing on the 4PC setting to enhance security and efficiency in MLaaS.
Unknown
BLAZE introduces a blazing fast privacy-preserving machine learning framework that significantly accelerates secure computation for ML tasks.
Unknown
This paper proposes a privacy-preserving machine learning as a service framework using secure multi-party computation to enable model training and inference on encrypted data.
Unknown
Proposes Adversarial Representation Engineering (ARE), a general model editing framework that efficiently edits large language models by leveraging representation engineering.
Unknown
SHARP is a representation-level intervention framework that modulates hallucination in LVLMs by steering internal representations.