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

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…

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…

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.

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

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

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…

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.

This paper investigates the robustness of world models in vision-based quadrotor navigation and identifies factors governing their quality.

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

Weak self-training on synthetic data can amplify a language model's existing capabilities, but this effect is strictly dependent on the compatibility between the source and student models, not on the…

This paper proposes a new training objective for sample-based generative models that considers decision maker's cost structure.

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

The paper introduces 3DCodeBench, a systematic benchmark and platform for evaluating Vision-Language Model (VLM) agents' ability to generate procedural 3D models from text and images using code.

The paper proposes a persona-based evaluation framework that replaces monolithic AI benchmarks with structured cognitive profiles to capture diverse human perspectives, while also identifying the chal…

This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…

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

The paper introduces a new quantitative metric, Contextual Alternative Choice (CAC), to rigorously test language models' syntactic and functional understanding of determiners, showing that current mod…