This paper proposes a semi-supervised framework, RepG, for conditional generative modeling using stochastic interpolation and low-dimensional latent representations.

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

Introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs) for generating outputs of varying sizes in continuous and discrete state spaces.

This paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end, resolving the issue of non-differentiable VQ indices.

The paper proposes a context-weighted sampler and scaled cross-entropy loss function for discrete generative modeling to improve generation quality and reduce generative perplexity.

The paper introduces Label-Augmented Conditional Diffusion (LACD), a method for learning complex conditional distributions using unlabeled data, and provides theoretical guarantees for its effectivene…

The paper introduces Conformal Generation (Conf-Gen), a novel framework that adapts conformal risk control to provide formal uncertainty guarantees for unsupervised generative models like LLMs and ima…

The paper introduces the Insertion Process (IP), a novel stochastic generative model that learns variable-length, non-monotonic sequence generation by explicitly modeling the insertion order of tokens…

This paper introduces gradient inference, a new approach to developing sound and efficient gradient estimators for probabilistic programs by reducing gradient estimation to a related probabilistic inf…

Introduces Posterior Prefix Tuning (PPT) for eliciting high-utility continuations from Bayes-filtered transformers using a latent posterior model.

The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual gener…

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

The paper introduces a hybrid WGAN-GA framework that uses a Genetic Algorithm (GA) to refine graphs generated by a GAN, significantly reducing structural deviations and improving realism.

The paper introduces Diversity-inducing Initialization (DivIn), a novel method that improves image diversity by re-weighting the initial noise selection based on the guidance potential, thereby mitiga…

This paper proposes a new definition of source in source tracing as a compositional tuple of Architecture, Training Data, and other training factors, and introduces a framework using Structured Orthon…

The paper repurposes a pre-trained speech classifier as the backbone for diffusion generation, reducing the need for two separately trained models.