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

The paper proposes VLBM, a latent basis modeling framework, to achieve state-of-the-art robustness in multivariate time series forecasting, particularly when facing rare but high-impact out-of-distrib…

The paper introduces the Computation-Aware State-Space Model (CASSM), a novel framework that extends Bayesian methods to handle model selection and large state-spaces, achieving competitive performanc…

The paper introduces C$^2$R (Cross-sample Consistency Regularization) to address feature splitting and absorption issues in Sparse Autoencoders by encouraging consistent latent assignment across sampl…

This paper proposes a Multi-stage Constrained Optimization Framework (MCOF) for Variational Autoencoders (VAEs) to address challenges in sampling, identifying active decision variables, and enforcing…

The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring s…

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

This paper improves the foundations of neural likelihood approximation for Bayesian inverse problems by making the learning problem strictly convex and showing convergence to the true likelihood.

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.

This paper introduces ATLAS, a method for disentangling invariant and heterogeneous factors in multi-environment factor models, enabling transferable prediction and robust invariant-factor-only predic…

This paper proposes methods to improve the encoding capacity and disentanglement of Variational Autoencoders (VAE) by imposing entropy-based constraints and a weight-filter method.

iLoRA introduces a novel Bayesian graph-conditioned LoRA framework that jointly learns prediction and latent interaction structure, significantly improving microbiome diagnosis by modeling microbe-mic…

VITAL introduces a novel latent-space reasoning framework for medical MLLMs, utilizing visual-semantic dual supervision to enhance reasoning capabilities and provide crucial interpretability without s…

BayesNCL introduces a probabilistic gating mechanism to resolve the optimization conflict in Contrastive Learning, leading to highly disentangled and semantically consistent representations.